© 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. 11-RESID-POST-AA
    11. 109987
    Prev
    Next
    INDEX
    Explanations

    inspect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    scatter
    -0.07
    _ACC
    -0.07
     dynamically
    -0.07
    abe
    -0.07
    -0.07
    ちは
    -0.07
    project
    -0.07
    ,@
    -0.07
     shuffle
    -0.07
    ิด
    -0.07
    POSITIVE LOGITS
     disclosures
    0.11
     inspections
    0.10
     disclosure
    0.10
     compradores
    0.10
     disclose
    0.09
    Informe
    0.09
     reconnaissance
    0.09
     వెల్లడ
    0.09
     forensic
    0.09
     homeowners
    0.09
    Activations Density 0.009%
    No Known Activations