© 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. 22888
    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
     خپلې
    -0.10
     their
    -0.10
     desirable
    -0.09
     beliebt
    -0.09
     خپله
    -0.09
     gerne
    -0.09
     njihov
    -0.09
     ತಮ್ಮ
    -0.09
     उनकी
    -0.08
     അവരുടെ
    -0.08
    POSITIVE LOGITS
     adjustments
    0.12
     suficientes
    0.12
     ajustes
    0.12
     adjust
    0.11
    adjust
    0.11
     enough
    0.11
     suficiente
    0.11
     necessário
    0.11
     genoeg
    0.11
    Adjust
    0.11
    Activations Density 0.005%

    No Known Activations