© 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. 99378
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .SUB
    -0.07
    зат
    -0.07
    .O
    -0.07
    عديل
    -0.07
    געה
    -0.07
     கட்ட
    -0.07
     произ
    -0.07
    .Dependency
    -0.07
    -setting
    -0.07
     Votre
    -0.07
    POSITIVE LOGITS
     Mats
    0.09
     unde
    0.08
     avis
    0.08
    Browse
    0.08
     Eva
    0.08
     fis
    0.08
    々
    0.08
    东西
    0.07
     Adele
    0.07
     fetched
    0.07
    Activations Density 0.021%

    No Known Activations