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. 88339
    Prev
    Next
    INDEX
    Explanations

    graphic

    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
     hippoc
    -0.09
     naap
    -0.08
    统一
    -0.08
    (SQLite
    -0.08
    ypass
    -0.08
     fauteuil
    -0.08
    RCT
    -0.07
    lect
    -0.07
     atender
    -0.07
    ে�
    -0.07
    POSITIVE LOGITS
     spikes
    0.08
     deleted
    0.07
     содержит
    0.07
     liner
    0.07
     WIN
    0.07
     Bb
    0.07
     Staying
    0.07
     LIVE
    0.07
     bmp
    0.07
     boosting
    0.07
    Activations Density 0.007%

    No Known Activations