© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29637
    Prev
    Next
    INDEX
    Explanations

    superseding other agreements/offers

    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
     龙
    -0.08
     मुताबिक
    -0.08
     realistically
    -0.08
    宝宝
    -0.08
     কয়
    -0.08
    龙
    -0.08
     अनुसार
    -0.08
    اسب
    -0.08
    ॉन
    -0.07
    ashen
    -0.07
    POSITIVE LOGITS
     conversations
    0.08
     hiện
    0.08
     vacations
    0.07
     tubes
    0.07
     ä
    0.07
     CONCAT
    0.07
     hunger
    0.07
     instru
    0.07
     резерв
    0.07
     yh
    0.07
    Activations Density 0.003%

    No Known Activations