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. 15-RESID-POST-AA
    6. 19147
    Prev
    Next
    INDEX
    Explanations

    HTML image tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mink
    -0.08
     improvis
    -0.08
    ublishing
    -0.08
    荒
    -0.08
     insightful
    -0.08
     publishing
    -0.08
     Overflow
    -0.07
     literary
    -0.07
     Map
    -0.07
     Mongo
    -0.07
    POSITIVE LOGITS
     CGSize
    0.10
    尺寸
    0.10
    _height
    0.09
    นาด
    0.09
     taimi
    0.09
     आकार
    0.09
    CGSize
    0.09
    50
    0.09
    -icons
    0.08
     ICON
    0.08
    Activations Density 0.002%

    No Known Activations