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. 98110
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
    andest
    -0.08
    gång
    -0.08
    ilty
    -0.07
     tumult
    -0.07
    ्ञ
    -0.07
    čki
    -0.07
    ्च
    -0.07
    Wu
    -0.07
     بچے
    -0.07
    ген
    -0.07
    POSITIVE LOGITS
    озит
    0.11
    лека
    0.11
    озя
    0.11
    ádza
    0.10
    од
    0.10
    ожу
    0.10
    ивая
    0.09
    но
    0.09
    орач
    0.09
    ádz
    0.09
    Activations Density 0.003%

    No Known Activations