Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112493
    Prev
    Next
    INDEX
    Explanations

    binomial coefficients

    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
     Duty
    -0.08
     duty
    -0.08
    (start
    -0.08
    Duty
    -0.08
    (expr
    -0.07
     DEL
    -0.07
    쳐
    -0.07
    (pro
    -0.07
     tipe
    -0.07
     starts
    -0.07
    POSITIVE LOGITS
     പിന്നീട്
    0.09
    068
    0.09
     назад
    0.09
     ઘટાડ
    0.09
     પાછ
    0.09
     തെള
    0.09
     takaisin
    0.09
     ശേഷം
    0.08
     തുടർന്ന്
    0.08
     വിപ
    0.08
    Activations Density 0.005%

    No Known Activations