© 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. 24568
    Prev
    Next
    INDEX
    Explanations

    process

    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
     specially
    -0.08
    ್ತು
    -0.07
     punkt
    -0.07
    �
    -0.07
    ಸ್ಥ
    -0.07
    (tm
    -0.07
     Corse
    -0.07
    .pixel
    -0.07
     spécialement
    -0.07
     landscaping
    -0.07
    POSITIVE LOGITS
     równie
    0.09
     separar
    0.08
    Separ
    0.08
     separation
    0.08
    ale
    0.07
     separates
    0.07
     separating
    0.07
     Separ
    0.07
     venda
    0.07
    Altern
    0.07
    Activations Density 0.008%

    No Known Activations