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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 94349
    Prev
    Next
    INDEX
    Explanations

    Balinese culture/language

    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
    Not in Any Lists

    No Comments

    Negative Logits
     arterial
    -0.08
     evolutionary
    -0.08
     arteries
    -0.08
     artery
    -0.08
     aptitude
    -0.08
     GDP
    -0.07
    (socket
    -0.07
    Charles
    -0.07
     rod
    -0.07
     Erd
    -0.07
    POSITIVE LOGITS
    _nil
    0.10
     budaya
    0.10
     nil
    0.10
    nil
    0.10
     Nil
    0.10
     spirituality
    0.09
     overtu
    0.09
    Nil
    0.09
     hindu
    0.09
     भक्त
    0.09
    Activations Density 0.003%

    No Known Activations