© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65313
    Prev
    Next
    INDEX
    Explanations

    fraction

    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
     biggest
    -0.08
     Kirst
    -0.07
    kill
    -0.07
     lou
    -0.07
    eture
    -0.07
    authority
    -0.07
     destination
    -0.07
     kill
    -0.07
     resultant
    -0.07
     anti
    -0.07
    POSITIVE LOGITS
    ární
    0.08
    Gross
    0.07
    ศาสตร์
    0.07
     הבית
    0.07
    /ajax
    0.07
     wers
    0.07
     awkward
    0.07
    _html
    0.07
     rather
    0.07
     slightly
    0.07
    Activations Density 0.011%

    No Known Activations