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. 78683
    Prev
    Next
    INDEX
    Explanations

    zero or one

    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
     reasonably
    -0.08
     reasonable
    -0.08
    ="'
    -0.07
     Command
    -0.07
    ciones
    -0.07
     Equ
    -0.07
    Equ
    -0.07
    ▬
    -0.07
    ╝
    -0.07
    ал
    -0.07
    POSITIVE LOGITS
     wodurch
    0.11
     وبالتالي
    0.10
     त्यामुळे
    0.09
     Daher
    0.09
     그래서
    0.09
     Поэтому
    0.09
     Daardoor
    0.09
    ,因此
    0.09
     waardoor
    0.09
    filmer
    0.08
    Activations Density 0.067%

    No Known Activations