© 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 EvalsExportsinterp-engineNEWAPI 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. 22395
    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
     each
    -0.11
     ప్రతి
    -0.09
     {↵
    -0.09
    ↵
    -0.09
     ഓരോ
    -0.09
     Each
    -0.09
     jeweiligen
    -0.09
    ":↵↵
    -0.09
    Each
    -0.09
    ٔ
    -0.09
    POSITIVE LOGITS
     concluded
    0.12
     conclusion
    0.11
     reasoning
    0.11
     calculations
    0.11
     above
    0.11
     deduction
    0.11
     Conclusion
    0.10
     conclusions
    0.10
    Conclusion
    0.10
     deductions
    0.10
    Activations Density 0.117%

    No Known Activations