© 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. 19-RESID-POST-AA
    11. 102719
    Prev
    Next
    INDEX
    Explanations

    judgments, biases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     సందర్భ
    -0.08
     après
    -0.08
     عقب
    -0.07
     mientras
    -0.07
     terwijl
    -0.07
     while
    -0.07
     boodsch
    -0.07
     insieme
    -0.07
    ially
    -0.07
     समुदाय
    -0.07
    POSITIVE LOGITS
     판단
    0.13
    判断
    0.12
     judgments
    0.12
     biases
    0.11
    entscheidung
    0.11
     beoord
    0.11
     বিচার
    0.11
     arvio
    0.10
     영향을
    0.10
     bias
    0.10
    Activations Density 0.003%

    No Known Activations