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. 77561
    Prev
    Next
    INDEX
    Explanations

    SELinux

    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
    ాలలో
    -0.08
     몇
    -0.07
    ellipse
    -0.07
     oyunc
    -0.07
     참가
    -0.07
    ాలు
    -0.07
    ంలో
    -0.07
     станов
    -0.07
     হলে
    -0.07
    ాలకు
    -0.07
    POSITIVE LOGITS
    гой
    0.09
     specialise
    0.08
     specialised
    0.08
     specialises
    0.08
     Alps
    0.08
     sophisticated
    0.08
    詳細
    0.08
     Labrador
    0.08
     uninter
    0.08
     restrictive
    0.07
    Activations Density 0.001%

    No Known Activations