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. 74434
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     conson
    -0.08
     Runde
    -0.08
     Features
    -0.08
    هو
    -0.08
     conduce
    -0.08
     crossword
    -0.07
     Codable
    -0.07
     klok
    -0.07
     burl
    -0.07
     decid
    -0.07
    POSITIVE LOGITS
     forfe
    0.09
    deposit
    0.09
     withdrawals
    0.08
     ಠ
    0.08
     amount
    0.08
     liquidity
    0.08
    [msg
    0.08
    Amounts
    0.08
     Deposit
    0.08
     IERC
    0.08
    Activations Density 0.004%

    No Known Activations