Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90728
    Prev
    Next
    INDEX
    Explanations

    Radius, curvature, 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
     protein
    -0.09
     fungus
    -0.09
     fungi
    -0.09
     items
    -0.08
     Protein
    -0.08
     prote
    -0.08
     additions
    -0.08
     proteína
    -0.08
     fungal
    -0.08
     Sales
    -0.07
    POSITIVE LOGITS
     curvature
    0.11
     दूरी
    0.09
    -radius
    0.09
    _DISTANCE
    0.09
    vature
    0.09
    距
    0.09
    距离
    0.09
    -distance
    0.09
     tangent
    0.08
    lassical
    0.08
    Activations Density 0.015%

    No Known Activations