© 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. 99213
    Prev
    Next
    INDEX
    Explanations

    ь

    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
    ുപ്പ്
    -0.07
    ાથ
    -0.07
    事項
    -0.07
     કે
    -0.07
     centre
    -0.07
     位
    -0.07
    ّي
    -0.07
    ിച്ച
    -0.07
    �ી
    -0.07
    ્તિ
    -0.07
    POSITIVE LOGITS
    _demo
    0.08
     onverw
    0.08
    "But
    0.08
     unexpectedly
    0.08
     Constit
    0.08
    ",(
    0.08
    üllen
    0.08
     있지만
    0.08
    ాలని
    0.08
    undo
    0.08
    Activations Density 0.168%

    No Known Activations