© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29049
    Prev
    Next
    INDEX
    Explanations

    errors

    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
    vector
    -0.09
    lamp
    -0.08
    _feat
    -0.08
    xz
    -0.08
    yards
    -0.08
    xampp
    -0.08
    др
    -0.08
    graf
    -0.08
    uman
    -0.08
    anoj
    -0.07
    POSITIVE LOGITS
     नीति
    0.10
     Strategies
    0.09
     Threshold
    0.09
     Strategy
    0.09
     Reject
    0.09
     Policies
    0.08
     Issues
    0.08
     Overflow
    0.08
    _policy
    0.08
     Policy
    0.08
    Activations Density 0.007%

    No Known Activations