Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 46887
    Prev
    Next
    INDEX
    Explanations

    C++ const/static keywords

    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
    aghan
    -0.08
     Sham
    -0.08
    alem
    -0.07
    kiye
    -0.07
    .Qu
    -0.07
    ubh
    -0.07
    wanda
    -0.07
    నే
    -0.07
     sham
    -0.07
    ぞ
    -0.07
    POSITIVE LOGITS
     선언
    0.08
     Clause
    0.08
     router
    0.08
     означ
    0.08
     допуска
    0.08
     declarations
    0.08
     Corps
    0.08
     시민
    0.08
     значит
    0.08
     clause
    0.08
    Activations Density 0.005%

    No Known Activations