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. 98440
    Prev
    Next
    INDEX
    Explanations

    have

    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
    мый
    -0.07
    clerc
    -0.07
    ihan
    -0.07
     joita
    -0.07
     නො
    -0.07
     которую
    -0.07
    мін
    -0.07
     whereby
    -0.07
    екс
    -0.06
     simplifying
    -0.06
    POSITIVE LOGITS
    有
    0.64
     有
    0.57
    ,有
    0.47
     memiliki
    0.46
    มี
    0.42
    、有
    0.41
     have
    0.39
    都有
    0.39
     имеют
    0.39
     mempunyai
    0.39
    Activations Density 0.218%

    No Known Activations