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. 30603
    Prev
    Next
    INDEX
    Explanations

    from

    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
    pickle
    -0.08
    βά
    -0.08
    sed
    -0.08
    tm
    -0.08
    etag
    -0.07
     coffee
    -0.07
    usual
    -0.07
    {'
    -0.07
    alternative
    -0.07
    akken
    -0.07
    POSITIVE LOGITS
     crease
    0.09
    (vertices
    0.09
     centroid
    0.09
     suburb
    0.09
    =root
    0.08
     होकर
    0.08
    射
    0.08
     oorspr
    0.08
    _VERT
    0.08
     vertices
    0.08
    Activations Density 0.018%

    No Known Activations