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. 19217
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
    ørn
    -0.07
    ’étais
    -0.07
    (epoch
    -0.07
    יל
    -0.07
     Lider
    -0.07
    ɛ
    -0.07
    Ответ
    -0.07
    Послед
    -0.07
     nostalgia
    -0.07
    (sess
    -0.07
    POSITIVE LOGITS
     pouvez
    0.09
     পারবেন
    0.08
     veuillez
    0.08
     দাবি
    0.07
     zv
    0.07
     définir
    0.07
     المختلف
    0.07
     préciser
    0.07
     مشخص
    0.07
    0.07
    Activations Density 0.000%

    No Known Activations