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. 11-RESID-POST-AA
    6. 58570
    Prev
    Next
    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semakin
    -0.08
     fogu
    -0.08
    迁
    -0.08
     barnet
    -0.08
    ివ్
    -0.08
     incênd
    -0.07
     acima
    -0.07
     Asc
    -0.07
     teng
    -0.07
     crater
    -0.07
    POSITIVE LOGITS
     व्य
    0.08
     MLS
    0.08
     Specifically
    0.08
     Anglican
    0.08
     खाली
    0.07
     Kl
    0.07
    .printf
    0.07
    。其中
    0.07
    ांत
    0.07
    Kl
    0.07
    Activations Density 0.335%

    No Known Activations