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. 43705
    Prev
    Next
    INDEX
    Explanations

    shell scripts/file paths

    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
    同性
    -0.10
     эми
    -0.09
     ঈ
    -0.09
     насы
    -0.09
     verzamelen
    -0.09
    rupa
    -0.08
     Valentines
    -0.08
     цвет
    -0.08
     интим
    -0.08
     тщательно
    -0.08
    POSITIVE LOGITS
    启动
    0.10
     maintenance
    0.09
    通常
    0.08
     chạy
    0.08
    .exe
    0.08
     запуск
    0.08
    .cmd
    0.08
     ચલ
    0.08
     ./
    0.08
    Console
    0.08
    Activations Density 0.010%

    No Known Activations