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. 98521
    Prev
    Next
    INDEX
    Explanations

    Variants of "please"

    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
    出了
    -0.10
     vieler
    -0.09
     verschiedener
    -0.09
    muş
    -0.09
     многих
    -0.09
    aturated
    -0.09
     seines
    -0.09
    appar
    -0.09
    ,又
    -0.09
     ছিল
    -0.09
    POSITIVE LOGITS
     please
    0.19
     пожалуйста
    0.19
    ください
    0.18
    联系我们
    0.18
     مراجعه
    0.18
     kontaktieren
    0.18
    お願
    0.17
    ぜひ
    0.16
     nhé
    0.16
    よろしく
    0.16
    Activations Density 1.114%

    No Known Activations