© 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. 23-RESID-POST-AA
    11. 97310
    Prev
    Next
    INDEX
    Explanations

    Tomcat Catalina configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ണ
    -0.08
     Rebel
    -0.08
     entrance
    -0.08
     Entrance
    -0.08
     Solution
    -0.08
    -resource
    -0.08
    Entrance
    -0.07
     kopen
    -0.07
    \uff
    -0.07
     procure
    -0.07
    POSITIVE LOGITS
    ρέ
    0.07
    956
    0.07
    atan
    0.07
     cozinha
    0.07
     rata
    0.07
    Peers
    0.07
    ina
    0.07
     Asus
    0.07
    �다
    0.07
    pez
    0.07
    Activations Density 0.003%

    No Known Activations