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

    Neuronpedia

    Jacobian LensNEW
    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. 63897
    Prev
    Next
    INDEX
    Explanations

    commas, and

    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
     carcinoma
    -0.08
     {}).
    -0.08
     bachelors
    -0.07
     زوج
    -0.07
     vaikka
    -0.07
     dictatorship
    -0.07
     powerhouse
    -0.07
     unir
    -0.07
    getitem
    -0.07
    แด
    -0.07
    POSITIVE LOGITS
    字体
    0.09
    Typography
    0.08
    ommen
    0.08
     masc
    0.08
     texture
    0.08
     शैली
    0.07
     font
    0.07
     ornaments
    0.07
     stamina
    0.07
     色
    0.07
    Activations Density 0.075%

    No Known Activations