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. 58625
    Prev
    Next
    INDEX
    Explanations

    technical & measurement contexts

    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
     განათ
    -0.09
     გამოიყენ
    -0.09
     tirhisa
    -0.08
     Türkmenistanyň
    -0.08
     bedtime
    -0.08
    ուցիչ
    -0.08
     onmidd
    -0.08
    �
    -0.08
     bolýar
    -0.08
     рәиси
    -0.08
    POSITIVE LOGITS
     a
    0.09
     
    0.09
     for
    0.08
    (
    0.08
    ...
    0.08
    _
    0.08
    ,
    0.08
     occasional
    0.08
     the
    0.08
    "
    0.08
    Activations Density 0.461%

    No Known Activations