© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6412
    Prev
    Next
    INDEX
    Explanations

    scope and logic

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    روز
    -0.09
     Netanyahu
    -0.08
    Mongo
    -0.08
    主任
    -0.08
     Mongo
    -0.08
     Republican
    -0.08
     شعب
    -0.08
     האדם
    -0.08
     Mia
    -0.08
     Republicans
    -0.08
    POSITIVE LOGITS
     logic
    0.14
     osc
    0.14
    scope
    0.14
     scope
    0.13
     Scope
    0.13
     Logic
    0.13
    Scope
    0.13
     oscill
    0.12
     Osc
    0.12
    Logic
    0.12
    Activations Density 0.005%

    No Known Activations