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. 130938
    Prev
    Next
    INDEX
    Explanations

    requests and quick actions

    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
    عديد
    -0.11
     querendo
    -0.10
     ઘણ
    -0.10
     상당
    -0.10
     निकै
    -0.09
     podendo
    -0.09
     énormément
    -0.09
     numerosas
    -0.09
     العديد
    -0.09
     بسیار
    -0.09
    POSITIVE LOGITS
     пожалуйста
    0.16
     please
    0.15
     carefully
    0.15
     NOW
    0.14
     quickly
    0.14
     now
    0.14
     quick
    0.14
     asap
    0.14
    吧
    0.14
    一下
    0.14
    Activations Density 0.081%

    No Known Activations