Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43267
    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
    86
    -0.09
    Gp
    -0.08
     Chess
    -0.08
     chess
    -0.08
    침
    -0.07
    ainan
    -0.07
     cyclone
    -0.07
    daa
    -0.07
    Chess
    -0.07
     Bach
    -0.07
    POSITIVE LOGITS
     modific
    0.09
     cov
    0.08
     covariance
    0.07
    pleasant
    0.07
     purchase
    0.07
     производится
    0.07
    仕事内容
    0.07
    ವರಿಗೆ
    0.07
     cont
    0.07
     acomod
    0.07
    Activations Density 0.000%

    No Known Activations