© 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. 47543
    Prev
    Next
    INDEX
    Explanations

    pieces

    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
     grams
    -0.09
    Ra
    -0.07
    fi
    -0.07
    Grant
    -0.07
     ಸ
    -0.07
    Ro
    -0.07
    zt
    -0.07
     tid
    -0.07
     Betreiber
    -0.07
    crit
    -0.07
    POSITIVE LOGITS
     lég
    0.08
    /by
    0.08
    (Co
    0.07
     existem
    0.07
    Â
    0.07
     housing
    0.07
     evangelical
    0.07
     gauche
    0.07
    ыту
    0.07
     temples
    0.07
    Activations Density 0.088%

    No Known Activations