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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70919
    Prev
    Next
    INDEX
    Explanations

    Political commentary

    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
     Behavior
    -0.07
     sku
    -0.07
    Workspace
    -0.07
     แล้ว
    -0.07
     klanten
    -0.07
    ORM
    -0.07
     behave
    -0.07
     Workspace
    -0.07
    itial
    -0.07
     amt
    -0.07
    POSITIVE LOGITS
     conspiracy
    0.12
     alleging
    0.11
     misguided
    0.10
     allegations
    0.10
     blaming
    0.10
     conspir
    0.10
     alleged
    0.10
     негатив
    0.09
     activist
    0.09
     miscon
    0.09
    Activations Density 0.195%

    No Known Activations