© 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. 75460
    Prev
    Next
    INDEX
    Explanations

    235

    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
     tect
    -0.07
    (Intent
    -0.07
     monarchy
    -0.07
     власт
    -0.07
    utm
    -0.06
    Intent
    -0.06
     നിയമ
    -0.06
     exig
    -0.06
     implic
    -0.06
     modifiers
    -0.06
    POSITIVE LOGITS
     متن
    0.09
     sö
    0.08
    /videos
    0.08
     minib
    0.07
    作文
    0.07
     Bur
    0.07
     steamed
    0.07
     ans
    0.07
     leck
    0.07
     ಸಂಪ
    0.07
    Activations Density 36.386%

    No Known Activations