© 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 EvalsExportsAPI 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. 112348
    Prev
    Next
    INDEX
    Explanations

    Mueller investigation

    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
     habitats
    -0.09
     Habitat
    -0.08
     habitat
    -0.08
     powdered
    -0.08
     biomass
    -0.08
     sustainable
    -0.08
    áp
    -0.08
    push
    -0.07
     Sustainable
    -0.07
     अग्र
    -0.07
    POSITIVE LOGITS
     расслед
    0.13
     investigations
    0.11
     তদন্ত
    0.11
     investigation
    0.11
     subpo
    0.10
     subpoena
    0.10
     Investigation
    0.10
     Ermitt
    0.10
     impeachment
    0.10
     inquiry
    0.10
    Activations Density 0.050%

    No Known Activations