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. 164
    Prev
    Next
    INDEX
    Explanations

    of

    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
    科技
    -0.08
    ())));↵
    -0.08
     अपनी
    -0.07
    lotte
    -0.07
    slot
    -0.07
    script
    -0.07
     :)↵
    -0.07
    さら
    -0.07
    laugh
    -0.07
    !)↵
    -0.07
    POSITIVE LOGITS
     לבין
    0.09
    eft
    0.08
     необ
    0.08
    ર્વ
    0.08
     consequently
    0.08
    ද
    0.08
    عض
    0.08
     observable
    0.08
     sû
    0.08
     izany
    0.07
    Activations Density 0.008%

    No Known Activations