© 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. 75417
    Prev
    Next
    INDEX
    Explanations

    hoping

    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
    -logo
    -0.08
     продолжа
    -0.08
     Lange
    -0.08
    agree
    -0.08
    bg
    -0.07
     Mak
    -0.07
    anqu
    -0.07
     Literacy
    -0.07
     limitation
    -0.07
     Empfehlungen
    -0.07
    POSITIVE LOGITS
     bets
    0.08
     sú
    0.08
     NIL
    0.07
     cinqu
    0.07
     AA
    0.07
     unsuccess
    0.07
     fortune
    0.07
     typed
    0.07
    靠
    0.07
     وي
    0.07
    Activations Density 0.010%

    No Known Activations