© 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. 65360
    Prev
    Next
    INDEX
    Explanations

    one

    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
    .resize
    -0.09
    Implemented
    -0.09
    _resize
    -0.08
    Resize
    -0.08
    acement
    -0.07
    tant
    -0.07
    .ke
    -0.07
     évid
    -0.07
     Ging
    -0.07
    .true
    -0.07
    POSITIVE LOGITS
     perspectiva
    0.08
    跨度
    0.08
     Daw
    0.08
     rarely
    0.07
     potentially
    0.07
    Uber
    0.07
     pera
    0.07
     Aron
    0.07
     Nerv
    0.07
     ruk
    0.07
    Activations Density 0.023%

    No Known Activations