© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25939
    Prev
    Next
    INDEX
    Explanations

    saturation of electronic components

    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
    ammad
    -0.09
    thane
    -0.08
     Dimit
    -0.08
    薄
    -0.08
     ethan
    -0.08
    uelos
    -0.08
    rauch
    -0.08
    adzir
    -0.08
    녁
    -0.08
     despi
    -0.08
    POSITIVE LOGITS
    _range
    0.09
    	range
    0.09
     range
    0.09
    -range
    0.09
    范围
    0.09
     Range
    0.09
     maxima
    0.08
    Range
    0.08
     ±
    0.08
    .motor
    0.08
    Activations Density 0.004%

    No Known Activations