© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 108141
    Prev
    Next
    INDEX
    Explanations

    1

    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
     rô
    -0.08
     соответствии
    -0.07
     omgaan
    -0.07
    लेक
    -0.07
     Jednak
    -0.07
     bepaald
    -0.07
    flows
    -0.07
     planer
    -0.07
    Skipping
    -0.07
    $data
    -0.07
    POSITIVE LOGITS
    erca
    0.08
     him
    0.07
     seis
    0.07
     gor
    0.07
     ovo
    0.07
    통
    0.07
     caliber
    0.07
     بض
    0.07
    ümü
    0.07
     mode
    0.07
    Activations Density 0.003%

    No Known Activations