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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98344
    Prev
    Next
    INDEX
    Explanations

    。

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     बनाए
    -0.08
     XI
    -0.08
     **
    -0.08
    ✨
    -0.07
     &&
    -0.07
    ค์
    -0.07
     `
    -0.07
    dert
    -0.07
     ให้
    -0.07
     ทุก
    -0.07
    POSITIVE LOGITS
    状
    0.08
    িস্থিত
    0.08
    彩金
    0.08
    彩神
    0.08
    尼斯人
    0.08
    雪球
    0.08
     geared
    0.08
    柏
    0.08
     spiral
    0.08
    րում
    0.08
    Activations Density 0.005%

    No Known Activations