© 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. 23048
    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
    אָ
    -0.08
    Indeed
    -0.08
    �
    -0.08
    actually
    -0.07
     oziroma
    -0.07
    �
    -0.07
     folkl
    -0.07
    pam
    -0.07
     Indeed
    -0.07
    ərdə
    -0.07
    POSITIVE LOGITS
     memorize
    0.11
     calculation
    0.10
     уга
    0.10
     calculating
    0.10
     dozens
    0.10
     diagram
    0.09
     deduction
    0.09
     geleerd
    0.09
     calcul
    0.09
     nummers
    0.09
    Activations Density 0.048%

    No Known Activations