© 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. 3-RESID-POST-AA
    11. 2743
    Prev
    Next
    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     molding
    -0.08
    Clause
    -0.08
    rona
    -0.07
    Rom
    -0.07
    roong
    -0.07
     Ml
    -0.07
    _clause
    -0.07
     orta
    -0.07
    ulter
    -0.07
    LR
    -0.07
    POSITIVE LOGITS
     Marina
    0.08
     zal
    0.08
     deeply
    0.08
     Cre
    0.08
     estre
    0.07
     Huge
    0.07
     fé
    0.07
     rend
    0.07
     cre
    0.07
     Gonz
    0.07
    Activations Density 0.034%

    No Known Activations