© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68066
    Prev
    Next
    INDEX
    Explanations

    genes and biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تتح
    -0.08
     casserole
    -0.08
    购物
    -0.08
     paycheck
    -0.08
     taj
    -0.08
     Catalunya
    -0.08
     cart
    -0.08
    快捷
    -0.08
     leisurely
    -0.07
    忠
    -0.07
    POSITIVE LOGITS
     promising
    0.09
     biotech
    0.09
    .substr
    0.09
     biotechnology
    0.09
     Biotechnology
    0.09
     разработки
    0.09
     patented
    0.08
     Therapeut
    0.08
     predictive
    0.08
     Technology
    0.08
    Activations Density 0.048%

    No Known Activations