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. 98144
    Prev
    Next
    INDEX
    Explanations

    foreign languages and places

    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
    -t
    -0.08
    (t
    -0.08
     but
    -0.08
    .Step
    -0.07
     compar
    -0.07
    .t
    -0.07
    _t
    -0.07
     can
    -0.07
     certa
    -0.07
     moderna
    -0.07
    POSITIVE LOGITS
     Ebony
    0.09
     팬
    0.09
    ajia
    0.09
    ५०
    0.09
     yoğun
    0.09
     miał
    0.09
     Multiplayer
    0.08
     Women's
    0.08
    .apple
    0.08
     이유
    0.08
    Activations Density 0.000%

    No Known Activations