© 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. 24803
    Prev
    Next
    INDEX
    Explanations

    minimum

    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
     Hisp
    -0.09
     하나님
    -0.08
    acs
    -0.08
     lunes
    -0.08
     Nazis
    -0.07
     Compart
    -0.07
     Arrest
    -0.07
     aceasta
    -0.07
     Domaine
    -0.07
     iglesia
    -0.07
    POSITIVE LOGITS
     vigente
    0.08
     salarial
    0.08
     standards
    0.08
     publications
    0.08
    待遇
    0.08
     തൊഴ
    0.07
     statutory
    0.07
     stocking
    0.07
     paut
    0.07
     publishes
    0.07
    Activations Density 0.005%

    No Known Activations