© 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. 30955
    Prev
    Next
    INDEX
    Explanations

    equal signs

    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
     kula
    -0.08
    虚
    -0.08
    淡
    -0.07
    UTE
    -0.07
     footprint
    -0.07
     gerçek
    -0.07
     Through
    -0.07
    Through
    -0.07
     μέσω
    -0.07
     Maison
    -0.07
    POSITIVE LOGITS
    fügb
    0.09
     опять
    0.09
     следующий
    0.09
     результат
    0.08
    (update
    0.08
    Lucas
    0.08
     снова
    0.08
     новые
    0.08
    ,next
    0.08
     गुण
    0.08
    Activations Density 0.038%

    No Known Activations