© 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. 22825
    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
     дагы
    -0.08
     spezif
    -0.08
     некоторые
    -0.08
    _ads
    -0.08
     ಕೆಲವು
    -0.08
    (ignore
    -0.08
    (Servlet
    -0.08
     einigen
    -0.08
     ө
    -0.08
     гана
    -0.08
    POSITIVE LOGITS
     surpassed
    0.10
     पदार
    0.10
     surpass
    0.10
     prolific
    0.10
    夺
    0.10
     flest
    0.09
     récord
    0.09
     profanity
    0.09
    超过
    0.09
     career
    0.09
    Activations Density 0.009%

    No Known Activations