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. 49072
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
     wise
    -0.08
     escoger
    -0.08
     hush
    -0.08
     cientos
    -0.08
     před
    -0.08
     inefficient
    -0.07
     crank
    -0.07
     preferably
    -0.07
     lovingly
    -0.07
    度
    -0.07
    POSITIVE LOGITS
     Them
    0.08
    viol
    0.08
     Upgrade
    0.08
    Them
    0.08
    .typ
    0.07
     Cooler
    0.07
     Championship
    0.07
     Chir
    0.07
    xfa
    0.07
    vart
    0.07
    Activations Density 0.147%

    No Known Activations