© 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. 26626
    Prev
    Next
    INDEX
    Explanations

    largest

    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
    paar
    -0.08
     sidewalks
    -0.08
     um
    -0.08
     deta
    -0.08
     ถ่ายทอด
    -0.08
     Savannah
    -0.07
     количестве
    -0.07
    .remote
    -0.07
     wou
    -0.07
     kure
    -0.07
    POSITIVE LOGITS
    -largest
    0.09
     Dés
    0.08
    /top
    0.08
    谁
    0.08
    是谁
    0.08
    -ranking
    0.08
     lex
    0.07
    /root
    0.07
    之一
    0.07
     হিসেবে
    0.07
    Activations Density 0.019%

    No Known Activations