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. 12869
    Prev
    Next
    INDEX
    Explanations

    microscopy resolution

    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
    .Deserialize
    -0.08
     coursework
    -0.08
     touchdown
    -0.07
    仕事内容
    -0.07
     generously
    -0.07
     belles
    -0.07
     moderation
    -0.07
     yllä
    -0.07
     equipada
    -0.07
     grade
    -0.07
    POSITIVE LOGITS
    िध
    0.08
     Tell
    0.08
    'y
    0.08
    ’y
    0.08
     Limit
    0.08
     bwe
    0.08
    limit
    0.08
     Convert
    0.07
     listened
    0.07
     Majority
    0.07
    Activations Density 0.001%

    No Known Activations