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. 23-RESID-POST-AA
    6. 130760
    Prev
    Next
    INDEX
    Explanations

    non-English texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्या
    -0.10
    े
    -0.09
    ר
    -0.09
    et
    -0.09
    el
    -0.09
    )set
    -0.09
    en
    -0.09
    ار
    -0.09
    না
    -0.08
    ার
    -0.08
    POSITIVE LOGITS
    such
    0.10
    тобы
    0.09
    wepheshe
    0.09
    Such
    0.09
     such
    0.09
    ্ছে
    0.09
    ilega
    0.09
    ifukwa
    0.08
    aguzi
    0.08
     Such
    0.08
    Activations Density 0.041%

    No Known Activations