© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22870
    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
    Negative Logits
     perhaps
    -0.50
     möglicherweise
    -0.50
     vielleicht
    -0.48
     talvez
    -0.48
     ربما
    -0.46
     quizás
    -0.45
     možda
    -0.45
     måske
    -0.45
     possibly
    -0.45
     mungkin
    -0.44
    POSITIVE LOGITS
    ewise
    0.13
     exclusivement
    0.11
     ausschließlich
    0.11
     исключительно
    0.10
     exclusivamente
    0.10
     uitsluitend
    0.10
     only
    0.09
     wszystkie
    0.09
    elihood
    0.09
    Only
    0.09
    Activations Density 4.332%

    No Known Activations