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. 53971
    Prev
    Next
    INDEX
    Explanations

    document submission

    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
     Encore
    -0.08
    .listeners
    -0.08
    高手
    -0.08
    mega
    -0.08
    -0.07
     fuck
    -0.07
     desarroll
    -0.07
     mega
    -0.07
     desafíos
    -0.07
     Reload
    -0.07
    POSITIVE LOGITS
     ус
    0.09
     бұрын
    0.09
     مالی
    0.09
     éventuellement
    0.08
    Previous
    0.08
    née
    0.08
     eventueel
    0.08
     eyesight
    0.08
     financière
    0.08
     ಮನೆಯ
    0.08
    Activations Density 0.006%

    No Known Activations