© 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. 129306
    Prev
    Next
    INDEX
    Explanations

    constitutional

    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
     Unt
    -0.08
     unt
    -0.08
     potřeb
    -0.07
     dok
    -0.07
     zusamment
    -0.07
    <ul
    -0.07
     Corner
    -0.07
     Sm
    -0.07
     Scrap
    -0.07
     instala
    -0.07
    POSITIVE LOGITS
     parliamentary
    0.08
     wür
    0.08
     monarchy
    0.08
     свет
    0.08
    745
    0.07
     лу
    0.07
    Ansi
    0.07
     waist
    0.07
    106
    0.07
     facult
    0.07
    Activations Density 0.003%

    No Known Activations