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. 11-RESID-POST-AA
    6. 106279
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    autions
    -0.08
     Asi
    -0.08
     सम्ब
    -0.07
    Prix
    -0.07
     regelmatig
    -0.07
     soin
    -0.07
    Quat
    -0.07
     ವೈರ
    -0.07
     বন্ধ
    -0.07
     condenser
    -0.07
    POSITIVE LOGITS
    答案
    0.11
     ответы
    0.11
    .Yes
    0.10
     답
    0.10
     Antworten
    0.09
    答
    0.09
     Antwort
    0.09
     replies
    0.09
     answers
    0.09
     respostas
    0.09
    Activations Density 0.198%

    No Known Activations