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. 101658
    Prev
    Next
    INDEX
    Explanations

    polytopes

    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
     يؤ
    -0.09
     rivalry
    -0.09
     pesar
    -0.08
     парт
    -0.08
     محمود
    -0.08
     ن
    -0.08
     narration
    -0.08
    中文字幕
    -0.08
     dhaoine
    -0.08
     obra
    -0.08
    POSITIVE LOGITS
     convex
    0.10
    polygon
    0.10
    cube
    0.10
    _polygon
    0.10
     rectangular
    0.09
     polygon
    0.09
     polygons
    0.09
    Polygon
    0.09
    bounded
    0.09
     simplex
    0.08
    Activations Density 0.016%

    No Known Activations