© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21334
    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
     impec
    -0.09
     सैनिक
    -0.08
    onneur
    -0.08
    abatan
    -0.08
    制服
    -0.08
     sieve
    -0.08
    munition
    -0.08
     thrift
    -0.07
     Debian
    -0.07
    ientemente
    -0.07
    POSITIVE LOGITS
     positive
    0.09
     restructuring
    0.09
     desloc
    0.09
     mudança
    0.09
     تغيير
    0.09
     modifying
    0.09
     rewriting
    0.08
     تبدیلی
    0.08
    غيير
    0.08
     reposition
    0.08
    Activations Density 0.008%

    No Known Activations