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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106228
    Prev
    Next
    INDEX
    Explanations

    numerical values around 0 and 1

    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
    -et
    -0.08
     ára
    -0.08
    marketing
    -0.08
     administrations
    -0.08
     Appeal
    -0.07
     channels
    -0.07
     Administration
    -0.07
     administration
    -0.07
     Alphabet
    -0.07
    market
    -0.07
    POSITIVE LOGITS
    512
    0.08
    不可
    0.08
    341
    0.08
     unheard
    0.08
     chunky
    0.08
    !!
    0.07
    521
    0.07
    !(
    0.07
    637
    0.07
     Срби
    0.07
    Activations Density 0.005%

    No Known Activations