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. 56114
    Prev
    Next
    INDEX
    Explanations

    arthroscopy

    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
     kus
    -0.08
    担当
    -0.08
    体系
    -0.08
    -Ray
    -0.07
    났다
    -0.07
     luscious
    -0.07
     accented
    -0.07
     gambler
    -0.07
     juicy
    -0.07
    .family
    -0.07
    POSITIVE LOGITS
     plen
    0.09
    COL
    0.08
     troubleshooting
    0.08
     диагности
    0.08
     FLAG
    0.08
     corrective
    0.08
    .clean
    0.08
    ify
    0.08
     întâ
    0.08
     करके
    0.08
    Activations Density 0.004%

    No Known Activations