© 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. 22979
    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
     more
    -0.08
     particular
    -0.08
     diferente
    -0.07
    有所
    -0.07
     particularly
    -0.07
    某
    -0.07
    nå
    -0.07
     കൂടുതൽ
    -0.07
     Analyze
    -0.07
    特别
    -0.07
    POSITIVE LOGITS
    requires
    0.15
     requires
    0.14
    Requires
    0.13
     کیسے
    0.13
    How
    0.13
     如何
    0.13
     how
    0.13
     Requires
    0.13
    如何
    0.13
    how
    0.13
    Activations Density 0.052%

    No Known Activations