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. 15-RESID-POST-AA
    6. 18924
    Prev
    Next
    INDEX
    Explanations

    disagreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stə
    -0.07
     Card
    -0.07
     National
    -0.07
    -inch
    -0.07
     finne
    -0.07
    find
    -0.07
     find
    -0.07
     oppervlakte
    -0.07
     klein
    -0.07
    -size
    -0.07
    POSITIVE LOGITS
     disagreement
    0.14
     disag
    0.12
     disagreements
    0.12
     disagree
    0.12
     agreement
    0.11
    agreement
    0.10
     unanimous
    0.10
     unanim
    0.10
     Agreement
    0.10
    Agreement
    0.10
    Activations Density 0.012%

    No Known Activations