© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    猜你喜欢
    -0.08
    ាត
    -0.08
     Reliable
    -0.08
     megfelelő
    -0.08
    wynt
    -0.08
    asko
    -0.08
     responsibly
    -0.08
     exfol
    -0.08
     reliable
    -0.08
    følgelig
    -0.08
    POSITIVE LOGITS
     bureaucr
    0.29
     bureaucracy
    0.28
     cumbersome
    0.28
     burocr
    0.28
     бю
    0.22
    umbersome
    0.21
    bureau
    0.19
     tedious
    0.19
     burdens
    0.18
     paperwork
    0.18
    Activations Density 0.044%

    No Known Activations