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. 15-RESID-POST-AA
    6. 136
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ارين
    -0.09
    اران
    -0.08
     proteção
    -0.08
     patrimônio
    -0.08
     يمت
    -0.08
     beschermen
    -0.07
     cenas
    -0.07
     կունեն
    -0.07
    ের
    -0.07
    “四
    -0.07
    POSITIVE LOGITS
     tanpa
    0.16
    without
    0.16
     without
    0.15
     ohne
    0.15
     senza
    0.14
    _without
    0.14
    Without
    0.13
     ilman
    0.13
     χωρίς
    0.13
     zonder
    0.12
    Activations Density 0.065%

    No Known Activations