© 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. 11-RESID-POST-AA
    11. 114320
    Prev
    Next
    INDEX
    Explanations

    forms

    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
     divine
    -0.08
    (math
    -0.08
     ASP
    -0.07
     romance
    -0.07
     superiore
    -0.07
     omega
    -0.07
    นัก
    -0.07
     diet
    -0.07
     Tuscany
    -0.07
    നി
    -0.07
    POSITIVE LOGITS
     অভিয
    0.09
     напряж
    0.09
     стресс
    0.08
     ক্ষম
    0.08
     ಪ್ರಶ್ನ
    0.08
     Moral
    0.08
     힘
    0.08
     Ан
    0.08
     ಏ
    0.08
     конфликт
    0.08
    Activations Density 0.003%

    No Known Activations