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. 19119
    Prev
    Next
    INDEX
    Explanations

    without

    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
     légèrement
    -0.09
     Slight
    -0.09
     clairement
    -0.08
     slightly
    -0.08
     ligeramente
    -0.08
     थोड़ा
    -0.08
     مثلا
    -0.08
    主人
    -0.08
    -Owned
    -0.08
    Wear
    -0.08
    POSITIVE LOGITS
     headaches
    0.10
     ошибки
    0.10
     desapare
    0.10
     problematic
    0.10
     исчез
    0.09
     related
    0.09
     associated
    0.09
     woes
    0.09
     issues
    0.09
     desaparecer
    0.09
    Activations Density 0.005%

    No Known Activations