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. 15-RESID-POST-AA
    6. 26
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    ↵
    ↵
    -0.07
     *↵↵↵
    -0.07
     diketahui
    -0.07
     reasonably
    -0.07
    .*↵↵
    -0.07
     Taus
    -0.07
    िका
    -0.07
    .).↵↵
    -0.07
     Thursdays
    -0.07
     deut
    -0.07
    POSITIVE LOGITS
    რომ
    0.09
    <Base
    0.09
     najleps
    0.09
     með
    0.08
    ể
    0.08
    πό
    0.08
     pitanje
    0.08
    คิด
    0.08
    െ
    0.08
    /open
    0.08
    Activations Density 0.040%

    No Known Activations