© 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. 11-RESID-POST-AA
    11. 47275
    Prev
    Next
    INDEX
    Explanations

    medical conditions and injuries

    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
     مرکز
    -0.09
     কেন্দ্র
    -0.09
    ული
    -0.09
     centre
    -0.08
     centerpiece
    -0.08
     رقم
    -0.08
     Direkt
    -0.08
     مركز
    -0.08
     القسم
    -0.08
     pusat
    -0.08
    POSITIVE LOGITS
     माम
    0.13
     небольш
    0.12
     mild
    0.12
     nhẹ
    0.11
     subtle
    0.11
    軽
    0.10
     генә
    0.10
     harmless
    0.10
     minor
    0.10
     modest
    0.10
    Activations Density 0.083%

    No Known Activations