© 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. 23-RESID-POST-AA
    11. 48542
    Prev
    Next
    INDEX
    Explanations

    polygons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    浓
    -0.09
     thuốc
    -0.09
    position
    -0.09
     position
    -0.09
     Bluehost
    -0.08
     منتقل
    -0.08
     bcrypt
    -0.08
     pharmacy
    -0.08
     "~/
    -0.08
     uptime
    -0.08
    POSITIVE LOGITS
     polygons
    0.31
     polygon
    0.30
    _polygon
    0.28
    Polygon
    0.28
    polygon
    0.27
     Polygon
    0.26
    (vertices
    0.22
     vertices
    0.22
    Vertices
    0.22
    _vertices
    0.22
    Activations Density 0.109%

    No Known Activations