© 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. 63650
    Prev
    Next
    INDEX
    Explanations

    Injuries and hospitals

    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
    -moi
    -0.08
    -0.08
     revolución
    -0.07
     recordar
    -0.07
     apoyar
    -0.07
    アクセ
    -0.07
     mechanism
    -0.07
     புர
    -0.07
    -0.07
     sensing
    -0.07
    POSITIVE LOGITS
     hospitalized
    0.10
     went
    0.09
     filed
    0.09
    Went
    0.09
    进行了
    0.09
     interviewed
    0.09
     luka
    0.09
    Outlined
    0.08
     saddened
    0.08
     intensiv
    0.08
    Activations Density 0.052%
    No Known Activations