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. 97994
    Prev
    Next
    INDEX
    Explanations

    ф

    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
     расходы
    -0.08
    ogne
    -0.08
     zna
    -0.07
    kont
    -0.07
    kosten
    -0.07
     Ar
    -0.07
    _bad
    -0.07
    acid
    -0.07
    _unit
    -0.07
     deixam
    -0.07
    POSITIVE LOGITS
     khám
    0.09
    ास
    0.09
     Leip
    0.08
    asach
    0.08
    os
    0.08
    ాస
    0.07
     Kā
    0.07
     सहयोग
    0.07
    tsam
    0.07
     res
    0.07
    Activations Density 0.000%

    No Known Activations