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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78584
    Prev
    Next
    INDEX
    Explanations

    read

    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
     aquarium
    -0.09
    اخ
    -0.09
     ഇന്ന്
    -0.08
     Aquarium
    -0.08
     prevailed
    -0.08
     wurden
    -0.08
    eyay
    -0.08
     Modell
    -0.08
     ഫ്ര
    -0.08
     Wij
    -0.08
    POSITIVE LOGITS
    内容
    0.09
    Brief
    0.09
     내용
    0.08
     содержание
    0.08
    _contents
    0.08
     내용을
    0.08
     contents
    0.08
    Contents
    0.08
    Highlighted
    0.08
    Content
    0.08
    Activations Density 0.016%

    No Known Activations