© 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. 23098
    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
     their
    -0.10
     তাদের
    -0.10
     its
    -0.10
     either
    -0.10
     njihov
    -0.10
     THEIR
    -0.10
     તેમના
    -0.09
     শুধ
    -0.09
     їх
    -0.09
    其
    -0.09
    POSITIVE LOGITS
     demise
    0.12
     selves
    0.11
     backyard
    0.10
     handi
    0.10
     footsteps
    0.10
     mortality
    0.10
    身体
    0.10
     reflection
    0.10
    Reflection
    0.09
     handwriting
    0.09
    Activations Density 0.013%

    No Known Activations