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. 111683
    Prev
    Next
    INDEX
    Explanations

    light through cracks/windows

    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
    <QString
    -0.09
    دا
    -0.08
    classic
    -0.08
    געה
    -0.08
     excursions
    -0.08
    deposit
    -0.08
    גש
    -0.08
     deposito
    -0.08
     excursion
    -0.07
     Público
    -0.07
    POSITIVE LOGITS
     отверст
    0.08
     walls
    0.08
     waardoor
    0.08
    Walls
    0.08
    iper
    0.08
     ventilation
    0.08
    ಗಳಿಂದ
    0.08
     окно
    0.07
    шер
    0.07
     deceased
    0.07
    Activations Density 0.008%

    No Known Activations