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. 78085
    Prev
    Next
    INDEX
    Explanations

    economics

    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
    patterns
    -0.08
    hers
    -0.08
     betroffen
    -0.08
    -0.08
     patterns
    -0.08
    Patterns
    -0.08
    fault
    -0.08
    _patterns
    -0.08
     Patterns
    -0.08
    ിട
    -0.07
    POSITIVE LOGITS
     игрок
    0.09
     seseorang
    0.09
     ph
    0.09
     joueurs
    0.08
     sailors
    0.08
     settlers
    0.08
    -għ
    0.08
    arii
    0.08
    .Push
    0.08
     residents
    0.08
    Activations Density 0.001%

    No Known Activations