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. 98557
    Prev
    Next
    INDEX
    Explanations

    Code snippets using arrays

    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
    स्क
    -0.07
     秒
    -0.07
    ુર
    -0.07
    secure
    -0.07
    _freq
    -0.07
    _latest
    -0.07
    coordinates
    -0.07
    smart
    -0.07
    muje
    -0.07
    scope
    -0.07
    POSITIVE LOGITS
     specialize
    0.11
    ot
    0.10
    ots
    0.09
     oxide
    0.09
     display
    0.08
     specializes
    0.08
    otland
    0.08
    -I
    0.08
     gee
    0.08
    otin
    0.08
    Activations Density 0.001%

    No Known Activations