© 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. 29661
    Prev
    Next
    INDEX
    Explanations

    butt and woman

    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
    ৎস
    -0.09
    季度
    -0.09
    raform
    -0.08
     atroc
    -0.08
    ektion
    -0.08
     rotating
    -0.08
    Expense
    -0.08
     relaxing
    -0.08
    serialization
    -0.08
    ancio
    -0.08
    POSITIVE LOGITS
     ('
    0.08
     ഈ
    0.07
    _x
    0.07
     or
    0.07
     WIFI
    0.07
     ಈ
    0.07
     HAD
    0.07
     (`
    0.07
     declare
    0.07
     AD
    0.07
    Activations Density 0.000%

    No Known Activations