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

    Neuronpedia

    APICircuit 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. 12991
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     somehow
    -0.09
     сиг
    -0.09
     تمام
    -0.08
     she'll
    -0.08
     They'll
    -0.08
     binarias
    -0.08
     გამოს
    -0.08
     aquellas
    -0.08
     Slight
    -0.08
     cual
    -0.08
    POSITIVE LOGITS
     famously
    0.10
     famous
    0.09
    ,以及
    0.08
    µ
    0.08
    以及
    0.08
     وغيرها
    0.08
    Women
    0.08
     arguably
    0.08
     famoso
    0.08
     early
    0.07
    Activations Density 0.130%

    No Known Activations