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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26441
    Prev
    Next
    INDEX
    Explanations

    incentives

    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
     prost
    -0.08
    ضح
    -0.08
     Уч
    -0.07
     smaken
    -0.07
     теч
    -0.07
     Bags
    -0.07
    itat
    -0.07
    ρεύ
    -0.07
     nutric
    -0.07
    ittut
    -0.07
    POSITIVE LOGITS
     paradigm
    0.08
    EK
    0.07
    (sort
    0.07
    0.07
    (Abstract
    0.07
     Hindu
    0.07
    ，因此
    0.07
     herself
    0.07
    #define
    0.07
    _class
    0.07
    Activations Density 0.466%
    No Known Activations