© 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. 77828
    Prev
    Next
    INDEX
    Explanations

    主题

    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
     stati
    -0.08
     célé
    -0.07
     olsa
    -0.07
     fonctionner
    -0.07
     Ook
    -0.07
     unir
    -0.07
     इसे
    -0.07
     sā
    -0.07
    uhi
    -0.07
     jours
    -0.07
    POSITIVE LOGITS
     líderes
    0.10
     briefing
    0.09
    概要
    0.09
    gebiet
    0.09
     tem
    0.09
    andidato
    0.08
     summaries
    0.08
     Tem
    0.08
     clave
    0.08
     nineteenth
    0.08
    Activations Density 0.001%

    No Known Activations