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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 120272
    Prev
    Next
    INDEX
    Explanations

    description

    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
     Qa
    -0.08
     şah
    -0.08
     sara
    -0.08
     sre
    -0.08
     marriages
    -0.08
    ♥
    -0.08
     глед
    -0.08
     سعد
    -0.08
     ♥
    -0.08
     heta
    -0.08
    POSITIVE LOGITS
    描述
    0.13
     описание
    0.12
     Beschreibung
    0.11
    介绍
    0.11
     concise
    0.11
    简介
    0.11
     beschreibt
    0.11
    Описание
    0.11
    説明
    0.10
     describing
    0.10
    Activations Density 0.060%

    No Known Activations