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. 77244
    Prev
    Next
    INDEX
    Explanations

    Code imports

    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
     stressing
    -0.07
     seriousness
    -0.07
     stressed
    -0.07
     خانو
    -0.07
     Spots
    -0.07
     brill
    -0.07
    loe
    -0.07
     పట్ట
    -0.07
     hardcore
    -0.07
    价值
    -0.07
    POSITIVE LOGITS
     adicional
    0.09
     rsa
    0.08
     img
    0.08
    .additional
    0.08
    ุณ
    0.08
     electricidad
    0.08
    صاص
    0.08
    _reload
    0.08
     ayrıca
    0.08
     amad
    0.08
    Activations Density 0.006%

    No Known Activations