© 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. 18262
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
     चाहता
    -0.09
     éventuellement
    -0.09
     आदि
    -0.08
     Возможно
    -0.08
    ?),
    -0.08
     ಅದರ
    -0.08
     etc
    -0.08
     that'll
    -0.08
     möglicherweise
    -0.08
    ?-
    -0.08
    POSITIVE LOGITS
     amazing
    0.18
     incredible
    0.18
     incroyable
    0.17
     incrível
    0.16
     remarkable
    0.16
     fantastic
    0.16
     magnificent
    0.15
     phenomenal
    0.15
     brilliant
    0.15
     courageous
    0.15
    Activations Density 0.090%

    No Known Activations