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. 88266
    Prev
    Next
    INDEX
    Explanations

    OCR

    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
     elder
    -0.08
     htons
    -0.08
     abide
    -0.08
    aises
    -0.08
     aquarium
    -0.08
     precaution
    -0.08
     ethernet
    -0.08
    iais
    -0.08
    ANCES
    -0.08
     cleavage
    -0.08
    POSITIVE LOGITS
    -treated
    0.09
     OCR
    0.08
     handwriting
    0.08
     Kry
    0.08
    ;font
    0.08
     flair
    0.07
     font
    0.07
    OCR
    0.07
     текста
    0.07
    .font
    0.07
    Activations Density 0.004%

    No Known Activations