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. 76012
    Prev
    Next
    INDEX
    Explanations

    combat and rules

    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
    _:*
    -0.08
     adept
    -0.08
     ਕੇ
    -0.08
    _dep
    -0.08
     kons
    -0.08
    ansin
    -0.08
     Leid
    -0.08
     грамот
    -0.07
     miaka
    -0.07
     wasu
    -0.07
    POSITIVE LOGITS
    比赛
    0.15
    公平
    0.14
     tournament
    0.14
     प्रतियोग
    0.13
    竞技
    0.13
    Tournament
    0.13
    赛事
    0.13
     مسابق
    0.13
     соревн
    0.13
     contestants
    0.12
    Activations Density 0.071%

    No Known Activations