gpt-oss-safeguard-20b
OpenAIOpen weights
0
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
Context: 131K tokensReleased: Oct 29, 20250 up · 0 down
Reviews (0)
Sign in to vote and write a review.
No reviews yet — be the first to review gpt-oss-safeguard-20b.