© 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. 65576
    Prev
    Next
    INDEX
    Explanations

    test scoring

    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
     almacenamiento
    -0.09
     Manuel
    -0.09
     armazenamento
    -0.09
     Ante
    -0.08
    _STORAGE
    -0.08
     Plain
    -0.08
     Eine
    -0.08
    Eine
    -0.08
     पृथ
    -0.07
    श्म
    -0.07
    POSITIVE LOGITS
     penalty
    0.08
     инициатив
    0.08
    �
    0.08
     submission
    0.08
    Submit
    0.07
    gevallen
    0.07
    提交
    0.07
    Submitting
    0.07
     ચૂક
    0.07
     ставки
    0.07
    Activations Density 0.005%

    No Known Activations