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

    Neuronpedia

    APICircuit 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. 11979
    Prev
    Next
    INDEX
    Explanations

    ▼

    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
     accompanying
    -0.08
     explicitly
    -0.08
    ibri
    -0.07
    �
    -0.07
     slated
    -0.07
     detail
    -0.07
     accompany
    -0.07
     parentheses
    -0.07
     annotated
    -0.07
     >::
    -0.07
    POSITIVE LOGITS
     Tao
    0.07
     Samp
    0.07
    虎
    0.07
    ersion
    0.07
     роботи
    0.07
    .
    0.07
     bú
    0.07
     proses
    0.07
    toa
    0.07
     работу
    0.07
    Activations Density 0.000%

    No Known Activations