© 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. 108638
    Prev
    Next
    INDEX
    Explanations

    thermostability

    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
    ior
    -0.08
     dazzling
    -0.08
     principle
    -0.07
     principles
    -0.07
     exquisite
    -0.07
    ----</
    -0.07
     evangel
    -0.07
    chal
    -0.07
    ーー
    -0.07
     Principle
    -0.07
    POSITIVE LOGITS
     деятельности
    0.08
     sadrž
    0.08
    čkog
    0.08
     faaliyet
    0.08
     неожидан
    0.08
     définition
    0.08
     діяль
    0.08
    JPEG
    0.07
     surge
    0.07
    .anchor
    0.07
    Activations Density 0.000%

    No Known Activations