© 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. 8142
    Prev
    Next
    INDEX
    Explanations

    into

    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
     touching
    -0.07
     uth
    -0.07
     finit
    -0.07
     специальных
    -0.07
     lấy
    -0.07
    -0.07
     tempered
    -0.07
     началь
    -0.07
     Wiley
    -0.07
     reporter
    -0.07
    POSITIVE LOGITS
     clones
    0.09
    'om
    0.08
    Veel
    0.08
    ‟
    0.08
    قلاب
    0.08
    您的
    0.07
     hillside
    0.07
    ্ছেন
    0.07
    _existing
    0.07
     cùng
    0.07
    Activations Density 0.003%
    No Known Activations