© 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. 30449
    Prev
    Next
    INDEX
    Explanations

    dasein

    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
     rhetoric
    -0.08
     enthousiaste
    -0.08
    ück
    -0.08
    _percentage
    -0.08
    qh
    -0.08
    ース
    -0.08
     déclaré
    -0.08
    ary
    -0.07
    -Val
    -0.07
     youngest
    -0.07
    POSITIVE LOGITS
     inhab
    0.08
     edu
    0.08
     haus
    0.07
     unimaginable
    0.07
     heading
    0.07
     Vorm
    0.07
     nimi
    0.07
     Transporte
    0.07
    iteli
    0.07
     Karten
    0.07
    Activations Density 0.000%

    No Known Activations