© 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. 23110
    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
     Interrupted
    -0.10
     escolhido
    -0.09
     Choose
    -0.09
     પસંદ
    -0.09
    Choose
    -0.09
     gekozen
    -0.09
    Interrupted
    -0.09
     interrupted
    -0.09
     выбран
    -0.09
     ücret
    -0.08
    POSITIVE LOGITS
     reach
    0.15
     reaches
    0.15
     extent
    0.15
     পৌঁ
    0.14
     alcance
    0.13
    extent
    0.13
    Reach
    0.13
    reach
    0.13
     reaching
    0.12
     alcanza
    0.12
    Activations Density 0.014%

    No Known Activations