Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60494
    Prev
    Next
    INDEX
    Explanations

    returning

    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
     ढ
    -0.08
     बनाने
    -0.08
     লেখ
    -0.08
     بنانے
    -0.07
     автора
    -0.07
     മുന്ന
    -0.07
     બનાવવા
    -0.07
     प्रभ
    -0.07
     सीधे
    -0.07
     daunting
    -0.07
    POSITIVE LOGITS
     takaisin
    0.11
     refund
    0.11
     refunds
    0.11
    戻
    0.10
    追回
    0.10
     refunded
    0.10
     restit
    0.10
    退款
    0.10
    Refund
    0.10
     remboursement
    0.10
    Activations Density 0.008%

    No Known Activations