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. 44503
    Prev
    Next
    INDEX
    Explanations

    Obamacare / healthcare

    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
     locom
    -0.08
     perpendicular
    -0.08
    .command
    -0.08
     svn
    -0.08
     command
    -0.07
    _robot
    -0.07
    .de
    -0.07
     Fired
    -0.07
    xyz
    -0.07
     executes
    -0.07
    POSITIVE LOGITS
    insurance
    0.12
     coverage
    0.11
     Obamacare
    0.11
     Coverage
    0.10
     insurance
    0.10
    Insurance
    0.10
    amacare
    0.10
    Coverage
    0.10
     uninsured
    0.10
     Insurance
    0.10
    Activations Density 0.020%

    No Known Activations