© 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. 23070
    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
    oloogia
    -0.10
    ográfico
    -0.10
     Các
    -0.10
    iation
    -0.09
    rüstung
    -0.09
     Teile
    -0.09
     các
    -0.09
    izado
    -0.09
    's
    -0.09
     elementen
    -0.09
    POSITIVE LOGITS
     their
    0.18
     niiden
    0.18
     તેમની
    0.16
     उनके
    0.15
     তাদের
    0.15
     उनकी
    0.15
     олардың
    0.15
     उनका
    0.15
     jejich
    0.15
     leur
    0.14
    Activations Density 0.307%

    No Known Activations