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. 9198
    Prev
    Next
    INDEX
    Explanations

    guessed

    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
     verstre
    -0.07
     aceite
    -0.07
     ír
    -0.07
    Verification
    -0.07
     verify
    -0.07
     Verified
    -0.07
    иль
    -0.07
     #{@
    -0.07
     achieve
    -0.07
     crip
    -0.07
    POSITIVE LOGITS
    猜你
    0.12
    竞猜
    0.12
    猜
    0.11
     guessing
    0.10
    _guess
    0.10
     Guess
    0.10
     guessed
    0.10
     చాల
    0.10
    开奖号码
    0.09
     తెలుస
    0.09
    Activations Density 0.017%

    No Known Activations