© 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. 47200
    Prev
    Next
    INDEX
    Explanations

    smaller quantity

    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
     exige
    -0.08
     Retrieve
    -0.08
     eisen
    -0.08
    belasting
    -0.08
     NIL
    -0.08
     Ampl
    -0.07
    ления
    -0.07
    илли
    -0.07
    ertime
    -0.07
    ление
    -0.07
    POSITIVE LOGITS
    削
    0.12
    掉
    0.11
     తగ్గ
    0.10
    Than
    0.09
    Email
    0.09
    Compar
    0.09
    優惠
    0.09
    _than
    0.08
     baj
    0.08
    メール
    0.08
    Activations Density 0.017%

    No Known Activations