© 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. 45322
    Prev
    Next
    INDEX
    Explanations

    "Reply 1988"

    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
     suppressant
    -0.08
     रन
    -0.08
     bestehenden
    -0.08
     प्रणाली
    -0.08
    Run
    -0.08
     mathemat
    -0.08
    engl
    -0.08
     Run
    -0.08
     ветер
    -0.07
     हित
    -0.07
    POSITIVE LOGITS
     provincial
    0.09
     Bandung
    0.09
     전국
    0.09
    ㎡
    0.09
    爱情
    0.09
    머니
    0.09
    全国
    0.08
     village
    0.08
     layui
    0.08
    杭州
    0.08
    Activations Density 0.004%

    No Known Activations