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. 76474
    Prev
    Next
    INDEX
    Explanations

    long form text

    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
     LD
    -0.08
     Bij
    -0.07
     mạnh
    -0.07
    κεκρι
    -0.07
     ongem
    -0.07
     wez
    -0.07
    mittedly
    -0.07
     DE
    -0.07
     AV
    -0.07
     empire
    -0.07
    POSITIVE LOGITS
    har
    0.08
    er's
    0.08
     intenção
    0.07
     tumble
    0.07
    逊
    0.07
     تط
    0.07
    ters
    0.07
    .*")]↵
    0.07
    erv
    0.07
    टे
    0.07
    Activations Density 0.000%

    No Known Activations