© 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 EvalsExportsAPI 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. 20800
    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
     բաղ
    -0.10
    ეებს
    -0.10
    ქვამ
    -0.10
    აოდ
    -0.10
    ահայտ
    -0.10
    ("")){↵
    -0.10
     մասը
    -0.10
    േരള
    -0.10
    ေလး
    -0.10
     საშუალებას
    -0.10
    POSITIVE LOGITS
     and
    0.10
     и
    0.10
     Затем
    0.10
     અને
    0.09
     ...
    0.09
    then
    0.09
     ಮತ್ತು
    0.09
    そして
    0.09
     और
    0.09
    ---
    0.09
    Activations Density 0.007%

    No Known Activations