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. 106073
    Prev
    Next
    INDEX
    Explanations

    (F

    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
     jugu
    -0.08
     center
    -0.08
    ункт
    -0.08
     looping
    -0.07
    Center
    -0.07
    hema
    -0.07
    ன்ம
    -0.07
     Schedule
    -0.07
     שי
    -0.07
    循环
    -0.07
    POSITIVE LOGITS
     Valle
    0.09
    &eacute
    0.08
    \$
    0.08
     Vans
    0.08
     foto's
    0.07
     cukup
    0.07
     Bells
    0.07
    igue
    0.07
    \File
    0.07
     Laat
    0.07
    Activations Density 0.000%

    No Known Activations