© 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. 95429
    Prev
    Next
    INDEX
    Explanations

    day

    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
     Fluent
    -0.08
     toothbrush
    -0.08
    审
    -0.08
     cô
    -0.07
     freestyle
    -0.07
    atee
    -0.07
     Kā
    -0.07
     MIT
    -0.07
    .iterator
    -0.07
    .acquire
    -0.07
    POSITIVE LOGITS
    NUMBER
    0.09
    (integer
    0.09
     సంఖ్య
    0.09
     નંબર
    0.08
    zahlen
    0.08
     ಸಂಖ್ಯ
    0.08
    -number
    0.08
     ಸಂಖ್ಯೆ
    0.08
     номер
    0.08
    Number
    0.08
    Activations Density 0.007%

    No Known Activations