© 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. 23-RESID-POST-AA
    11. 5825
    Prev
    Next
    INDEX
    Explanations

    Computer code and mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sub
    -0.08
     sub
    -0.08
     Под
    -0.07
     N
    -0.07
     Click
    -0.07
     sch
    -0.07
    sub
    -0.06
    ２
    -0.06
    .sub
    -0.06
    30
    -0.06
    POSITIVE LOGITS
    -Or
    0.12
    -or
    0.11
    'US
    0.09
    Or
    0.09
    chol
    0.09
    _OR
    0.09
    .OR
    0.08
    FUL
    0.08
     Asa
    0.08
    (Component
    0.08
    Activations Density 0.003%

    No Known Activations