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. 58285
    Prev
    Next
    INDEX
    Explanations

    spirals

    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
     imports
    -0.08
     tenor
    -0.08
     aprob
    -0.08
    <Link
    -0.08
     appellate
    -0.08
     repudi
    -0.08
    <Http
    -0.08
    uran
    -0.08
     lík
    -0.08
     pār
    -0.08
    POSITIVE LOGITS
     clockwise
    0.12
     spiral
    0.10
     вращ
    0.10
     radius
    0.10
     Spiral
    0.10
     घूम
    0.10
     rotation
    0.10
     swirling
    0.09
     rectangular
    0.09
     zig
    0.09
    Activations Density 0.009%

    No Known Activations