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. 12753
    Prev
    Next
    INDEX
    Explanations

    >

    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
    Mons
    -0.08
    elesa
    -0.08
    tings
    -0.08
     ....↵
    -0.08
    خلق
    -0.07
     missile
    -0.07
    spaper
    -0.07
    писок
    -0.07
     peoples
    -0.07
    omething
    -0.07
    POSITIVE LOGITS
     caution
    0.09
    .note
    0.09
    怕
    0.09
     note
    0.09
     NOTE
    0.08
    注意
    0.08
    _DEBUG
    0.08
    .debug
    0.08
     DEV
    0.08
     ശ്രദ്ധ
    0.08
    Activations Density 0.015%

    No Known Activations