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. 101358
    Prev
    Next
    INDEX
    Explanations

    draws

    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
     spécialisée
    -0.09
     profund
    -0.09
     конф
    -0.08
     amafaranga
    -0.08
     située
    -0.08
     getenv
    -0.08
     Fontaine
    -0.08
     глуб
    -0.08
     paginate
    -0.08
     rémun
    -0.08
    POSITIVE LOGITS
    Polygon
    0.10
    Polyline
    0.09
     polygon
    0.09
    Vertices
    0.09
    _polygon
    0.09
     আঁ
    0.09
     çiz
    0.09
     Welding
    0.09
     dibujo
    0.09
    polygon
    0.09
    Activations Density 0.014%

    No Known Activations