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. 90696
    Prev
    Next
    INDEX
    Explanations

    thermic effect

    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
     شارع
    -0.09
    bem
    -0.09
    िस्ट
    -0.08
    ינטרנט
    -0.08
     alian
    -0.08
    昌
    -0.08
     entrevist
    -0.08
    ặt
    -0.07
    .inv
    -0.07
    ושב
    -0.07
    POSITIVE LOGITS
     spinning
    0.08
     子
    0.08
     folding
    0.08
     therm
    0.08
    Cuisine
    0.08
     energetic
    0.08
     before
    0.07
    nergie
    0.07
    'énergie
    0.07
     spun
    0.07
    Activations Density 0.003%

    No Known Activations