gpt-oss-safeguard is an open weight reasoning model from OpenAI specifically trained for safety classification tasks to help classify text content based on customizable policies. As a fine-tuned version of gpt-oss, gpt-oss-safeguard is designed to follow explicit written policies that you provide. This enables bring-your-own-policy Trust & Safety AI, where your own taxonomy, definitions, and thresholds guide classification decisions. Well crafted policies unlock gpt-oss-safeguard's reasoning capabilities, enabling it to handle nuanced content, explain borderline decisions, and adapt to contextual factors.

Who should use gpt-oss-safeguard?

gpt-oss-safeguard is designed for users who need real-time context and automation at scale, including:

• ML/AI Engineers working on Trust & Safety systems who need flexible content moderation
• Trust & Safety Engineers building or improving moderation, Trust & Safety, or platform integrity pipelines
• Technical Program Managers overseeing content safety initiatives
• Developers building projects/applications that require contextual, policy-based content moderation
• Policy Crafters defining what is accepted by an organization who want to test out policy lines, generate examples, and evaluate content

Run gpt-oss-safeguard locally

Download either the 20B or 120B variant into your LM Studio, by using the GUI or with lms in your terminal:

# download the 20b variant
lms get openai/gpt-oss-safeguard-20b

# download the 120b variant
lms get openai/gpt-oss-safeguard-120b

Then utilize LM Studio's SDK or OpenAI Responses API compatibility mode to use the model from your own code.

How oss-safeguard uses Policy Prompts

gpt-oss-safeguard is designed to use your written policy as its governing logic. While most models provide a confidence score based on the features it was trained on and require retraining for any policy changes, oss-safeguard makes decisions backed by reasoning within the boundaries of a provided taxonomy. This feature lets T&S teams deploy oss-safeguard as a policy-aligned reasoning layer within existing moderation or compliance systems. This also means that you can update or test new policies instantly without retraining the entire model.

Example Policy Prompts

## Policy Definitions

### Key Terms

**[Term 1]**: [Definition]

**[Term 2]**: [Definition]

**[Term 3]**: [Definition]

## Content Classification Rules

### VIOLATES Policy (Label: 1)
Content that:
- [Violation 1]
- [Violation 2]
- [Violation 3]
- [Violation 4]
- [Violation 5]

### DOES NOT Violate Policy (Label: 0)
Content that is:
- [Acceptable 1]
- [Acceptable 2]
- [Acceptable 3]
- [Acceptable 4]
- [Acceptable 5]

## Examples

### Example 1 (Label: 1)
**Content**: "[Example]"

**Expected Response**:

### Example 2 (Label: 1)
**Content**: "[Example]"

**Expected Response**:

### Example 3 (Label: 0)
**Content**: "[Example]"

**Expected Response**:

### Example 4 (Label: 0)
**Content**: "[Example]"

**Expected Response**:

License

gpt-oss-safeguard models are provided under the Apache-2.0 license.