© 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. 22958
    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
    Application
    -0.08
     application
    -0.08
     deep
    -0.08
    .some
    -0.07
    .signal
    -0.07
     diep
    -0.07
     other
    -0.07
     some
    -0.07
     tief
    -0.07
     people
    -0.07
    POSITIVE LOGITS
     davanti
    0.31
     أمام
    0.29
     davant
    0.28
     перад
    0.27
     foran
    0.26
     diante
    0.26
     delante
    0.26
     framför
    0.26
     সামনে
    0.26
     before
    0.25
    Activations Density 0.022%

    No Known Activations