© 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. 22842
    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
     Geo
    -0.10
    Geo
    -0.09
    .Geo
    -0.09
     toimit
    -0.08
    ordeaux
    -0.08
    dpi
    -0.08
     Garden
    -0.08
    Ingress
    -0.08
     Logs
    -0.08
     GEO
    -0.08
    POSITIVE LOGITS
     whisk
    0.18
     beaten
    0.16
     beat
    0.15
     beating
    0.15
     battre
    0.15
     whipping
    0.15
     brushing
    0.14
     vigorously
    0.14
     Beat
    0.13
     batter
    0.13
    Activations Density 0.047%

    No Known Activations