© 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. 924
    Prev
    Next
    INDEX
    Explanations

    computer connections and ports

    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
     nightmare
    -0.08
    .UTF
    -0.08
    _ROM
    -0.08
     furniture
    -0.08
    Pokemon
    -0.07
    during
    -0.07
     nostalgia
    -0.07
     during
    -0.07
    Fen
    -0.07
    isé
    -0.07
    POSITIVE LOGITS
     Outputs
    0.11
    输出
    0.11
    -output
    0.10
    这里只
    0.10
    /output
    0.10
     Eingang
    0.10
    _outputs
    0.10
     Output
    0.10
     输出
    0.10
    .outputs
    0.10
    Activations Density 0.004%

    No Known Activations