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. 130926
    Prev
    Next
    INDEX
    Explanations

    срав

    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
    av
    -0.10
     b
    -0.08
    avam
    -0.08
    aaa
    -0.08
    avale
    -0.08
    ालाई
    -0.08
     spatial
    -0.08
    oh
    -0.07
    आ
    -0.07
     ottaa
    -0.07
    POSITIVE LOGITS
    ни
    0.11
    ните
    0.10
    станавли
    0.10
    лага
    0.09
    chtigt
    0.09
    ೃದ್ಧ
    0.09
    нила
    0.09
     thấy
    0.08
    स्त
    0.08
     গেছে
    0.08
    Activations Density 0.001%

    No Known Activations