© 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. 30327
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    artan
    -0.08
    =<
    -0.08
     vui
    -0.07
    =<?
    -0.07
     irradi
    -0.07
    רים
    -0.07
    同时
    -0.07
    还能
    -0.07
     மிக
    -0.07
     கடந்த
    -0.07
    POSITIVE LOGITS
    ificent
    0.08
     goods
    0.08
    iant
    0.08
    -rating
    0.08
     વિભાગ
    0.08
     Literal
    0.08
     подраздел
    0.07
     Contributors
    0.07
     �
    0.07
     Sellers
    0.07
    Activations Density 0.110%

    No Known Activations