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. 15-RESID-POST-AA
    6. 19141
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daytime
    -0.12
     mornings
    -0.11
    凌晨
    -0.10
     nighttime
    -0.10
     সকালে
    -0.10
     утром
    -0.10
     सुबह
    -0.09
     afternoons
    -0.09
     daylight
    -0.09
     manhã
    -0.09
    POSITIVE LOGITS
     Brief
    0.09
     essentials
    0.09
     чаш
    0.09
     غذ
    0.08
     nutritious
    0.08
     Scholar
    0.08
     Personal
    0.08
     rapidement
    0.08
     стак
    0.08
     быст
    0.08
    Activations Density 0.008%

    No Known Activations