© 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. 22829
    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
     excels
    -0.09
     complies
    -0.08
     exceeds
    -0.08
     tends
    -0.08
     area
    -0.08
     dominates
    -0.07
     Rheinland
    -0.07
     beginnt
    -0.07
    Area
    -0.07
     área
    -0.07
    POSITIVE LOGITS
     listed
    0.12
    uggestions
    0.11
     descriptions
    0.11
     المختلفة
    0.10
     перечис
    0.10
     المذك
    0.10
     lists
    0.10
    .options
    0.10
     разные
    0.09
     specific
    0.09
    Activations Density 0.005%

    No Known Activations