© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102756
    Prev
    Next
    INDEX
    Explanations

    の

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     的
    -0.16
     का
    -0.13
     the
    -0.13
    的问题
    -0.12
    的
    -0.12
    的数据
    -0.12
     用户
    -0.11
     ਦਾ
    -0.11
    的人
    -0.11
     或
    -0.11
    POSITIVE LOGITS
    ため
    0.24
    よう
    0.23
    ೊಂದಿಗೆ
    0.21
    みに
    0.19
     জন্য
    0.19
     সাথে
    0.17
    ことで
    0.16
     মতো
    0.16
     মধ্যে
    0.16
     দিকে
    0.15
    Activations Density 0.004%

    No Known Activations