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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29771
    Prev
    Next
    INDEX
    Explanations

    org

    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
     vírus
    -0.08
     CAGR
    -0.08
     revamped
    -0.08
     diversion
    -0.08
     �
    -0.07
    .net
    -0.07
    �
    -0.07
    igeria
    -0.07
     infectious
    -0.07
     Latino
    -0.07
    POSITIVE LOGITS
    Locate
    0.09
     landlord
    0.08
     endpoint
    0.08
     exposing
    0.08
     locating
    0.08
     barns
    0.08
     двер
    0.08
     properties
    0.07
    ände
    0.07
     Barn
    0.07
    Activations Density 0.001%

    No Known Activations