© 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. 11-RESID-POST-AA
    11. 71641
    Prev
    Next
    INDEX
    Explanations

    Cultural traditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     monot
    -0.08
     Logged
    -0.08
    árm
    -0.08
     submar
    -0.08
    收益
    -0.08
     Snapshot
    -0.08
    Chooser
    -0.08
     FITNESS
    -0.08
     Logitech
    -0.08
     concussion
    -0.08
    POSITIVE LOGITS
     Senegal
    0.14
     Yoruba
    0.14
     indigenous
    0.13
     Indigenous
    0.13
     Kerala
    0.13
     vibrant
    0.12
     Rajasthan
    0.12
     diaspora
    0.12
     culturally
    0.12
     Nigerian
    0.12
    Activations Density 0.122%

    No Known Activations