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. 30750
    Prev
    Next
    INDEX
    Explanations

    on

    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
     ಗ್ರಾಮ
    -0.08
     कृषि
    -0.08
     ग्रामीण
    -0.08
    gps
    -0.08
    platte
    -0.08
    directive
    -0.08
     courteous
    -0.08
     Hausa
    -0.08
     ساخت
    -0.07
    农业
    -0.07
    POSITIVE LOGITS
     comics
    0.14
     superhero
    0.12
    漫画
    0.12
    漫畫
    0.12
     superheroes
    0.12
     villains
    0.12
     comic
    0.12
     Comics
    0.12
     villain
    0.11
     Superman
    0.11
    Activations Density 0.077%

    No Known Activations