© 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. 54716
    Prev
    Next
    INDEX
    Explanations

    instructions/requests

    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
     Superior
    -0.08
    昭
    -0.08
     ఇ
    -0.07
    eco
    -0.07
    -land
    -0.07
    itori
    -0.07
     Tribunal
    -0.07
     eenvoudig
    -0.07
    庭
    -0.07
     વ્ય
    -0.07
    POSITIVE LOGITS
    pekte
    0.08
     강조
    0.08
     함께
    0.08
     uppercase
    0.08
     salar
    0.08
    krift
    0.08
     &,
    0.08
     werde
    0.08
     설명
    0.07
    uppercase
    0.07
    Activations Density 0.003%

    No Known Activations