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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112185
    Prev
    Next
    INDEX
    Explanations

    urgent

    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
    err
    -0.09
    kal
    -0.08
     lean
    -0.08
    ysin
    -0.08
    truct
    -0.07
    entos
    -0.07
    veloper
    -0.07
     purposely
    -0.07
     leaning
    -0.07
    kok
    -0.07
    POSITIVE LOGITS
     urgente
    0.12
     urgent
    0.11
     необходимость
    0.11
     необходимости
    0.10
     urgently
    0.10
     ضرورة
    0.10
     necesidad
    0.10
     behov
    0.10
     dring
    0.09
     potrz
    0.09
    Activations Density 0.022%

    No Known Activations