Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 43182
    Prev
    Next
    INDEX
    Explanations

    did

    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
    ous
    -0.08
    ély
    -0.07
     Poh
    -0.07
    .co
    -0.07
     mos
    -0.07
    画像
    -0.07
    hq
    -0.07
     mnog
    -0.07
     Mit
    -0.07
    軽
    -0.06
    POSITIVE LOGITS
    -нибудь
    0.08
    ริษ
    0.08
    riana
    0.08
    และ
    0.08
    ะแ
    0.08
    เกี่ยว
    0.08
     இல்லை
    0.08
    ไหม
    0.08
    หัส
    0.08
     která
    0.08
    Activations Density 0.064%

    No Known Activations