© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22124
    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
    Not in Any Lists

    No Comments

    Negative Logits
     celebrities
    -0.11
     businessmen
    -0.10
     colleagues
    -0.09
     collega's
    -0.09
     señora
    -0.09
     CEOs
    -0.09
     collègues
    -0.09
     zakelijke
    -0.09
     politicians
    -0.09
     executives
    -0.09
    POSITIVE LOGITS
     orphan
    0.15
     apprentice
    0.15
    少年
    0.14
     giovane
    0.13
     youngest
    0.13
     যুব
    0.13
     ಯುವ
    0.13
     young
    0.13
     ছেলে
    0.12
     jeune
    0.12
    Activations Density 0.064%

    No Known Activations