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. 98423
    Prev
    Next
    INDEX
    Explanations

    at

    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
     ouverture
    -0.08
     upholstery
    -0.08
     geçirilen
    -0.08
     vlog
    -0.08
     flop
    -0.08
     दु�
    -0.08
     Dut
    -0.08
     hut
    -0.08
     постепенно
    -0.08
    ��
    -0.08
    POSITIVE LOGITS
     Brands
    0.09
     Naz
    0.08
     Gateway
    0.08
     In
    0.08
     Lime
    0.08
     Inter
    0.08
     Road
    0.08
     Alta
    0.08
    Brands
    0.08
     High
    0.08
    Activations Density 0.001%

    No Known Activations