gpt-oss-safeguard-120b
gpt-oss-safeguard-120b is a downloadable safety-reasoning model derived from gpt-oss. It classifies text against a written policy supplied by the operator.
The supplied policy controls classification
The 120b release can run in a local serving stack. The guide provides deployment examples for the separate 20B and 120B models. Policy definitions and thresholds come from the supplied instructions, rather than one fixed moderation taxonomy.OpenAI and ROOST guide to gpt-oss-safeguard
Review the rule and the decision together
Practical guidance. For a complex policy, define the categories, exceptions and evidence required for a decision. Compare disagreement with human reviewers and retain their corrections. A detailed explanation should help a reviewer locate the governing rule, not replace that review.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | gpt-oss-safeguard-120b |
Related models
- gpt-oss-safeguard-20b
OpenAI ยท gpt-oss-safeguard
A downloadable 20B-class gpt-oss adaptation for policy-based text classification.
Launch date not confirmedDownloadable