© 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. 7-RESID-POST-AA
    11. 1387
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    、更
    -0.09
     المعلومات
    -0.08
     рынка
    -0.08
     niż
    -0.08
     Grade
    -0.08
     grade
    -0.08
    چے
    -0.08
    cont
    -0.08
    hint
    -0.08
    �
    -0.08
    POSITIVE LOGITS
    主人
    0.09
     seorang
    0.08
     rebels
    0.08
     быв
    0.08
     bull
    0.08
     pilgrims
    0.08
     	↵
    0.08
     protagonist
    0.08
     ένας
    0.08
     whereby
    0.07
    Activations Density 0.061%

    No Known Activations