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. 29930
    Prev
    Next
    INDEX
    Explanations

    places, names

    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
     ועוד
    -0.09
     ï
    -0.09
     మొద
    -0.08
     صح
    -0.08
     ಮೊದಲ
    -0.08
     "%",↵
    -0.08
     cycling
    -0.07
     والسي
    -0.07
     أول
    -0.07
     خاصة
    -0.07
    POSITIVE LOGITS
    机官网
    0.10
    洋
    0.09
    井空
    0.08
    播播
    0.08
    苹果版
    0.08
    线观看
    0.08
    钱怎么
    0.08
    平台代理
    0.08
    凰
    0.08
    պան
    0.08
    Activations Density 0.484%

    No Known Activations