Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43052
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     overseas
    -0.08
    -0.07
     波
    -0.07
    名单
    -0.07
    波
    -0.07
    455
    -0.07
    urder
    -0.07
     ilg
    -0.07
     toxicity
    -0.07
     axe
    -0.06
    POSITIVE LOGITS
    gui
    0.08
    capitalize
    0.08
    Breakfast
    0.08
     специал
    0.08
    উ
    0.07
    jú
    0.07
    ાધ
    0.07
     integrar
    0.07
    Dang
    0.07
     धर्म
    0.07
    Activations Density 0.000%

    No Known Activations