© 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. 3-RESID-POST-AA
    11. 1379
    Prev
    Next
    INDEX
    Explanations

    Soviet Union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hav
    -0.09
     olsun
    -0.08
     seasoning
    -0.08
     fingers
    -0.07
    ไม
    -0.07
     belongs
    -0.07
     Сонымен
    -0.07
     lg
    -0.07
     oysters
    -0.07
     auc
    -0.07
    POSITIVE LOGITS
    共产党
    0.10
    共产
    0.10
     sovi
    0.10
     communist
    0.09
     Lenin
    0.09
     Stalin
    0.09
     USSR
    0.09
    社会主义
    0.09
    总书记
    0.09
    习近平
    0.09
    Activations Density 0.084%

    No Known Activations