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. 106126
    Prev
    Next
    INDEX
    Explanations

    general English 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
     প্রত
    -0.08
    (customer
    -0.08
    Ez
    -0.08
     পরিবার
    -0.07
    ekin
    -0.07
    浩
    -0.07
    282
    -0.07
    _now
    -0.07
    ジ
    -0.07
     tipe
    -0.07
    POSITIVE LOGITS
     additional
    0.13
    Additional
    0.13
     Additional
    0.12
     adicional
    0.12
     supplementary
    0.12
     aanvullende
    0.11
    additional
    0.11
     अतिरिक्त
    0.11
     secondary
    0.11
    .additional
    0.11
    Activations Density 0.428%

    No Known Activations