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

    Neuronpedia

    Jacobian LensNEW
    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. 112640
    Prev
    Next
    INDEX
    Explanations

    help

    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
    DAP
    -0.08
     PGA
    -0.08
     PSG
    -0.08
     Leap
    -0.08
     statue
    -0.08
    artz
    -0.07
    ärk
    -0.07
    olden
    -0.07
     Ист
    -0.07
     Dino
    -0.07
    POSITIVE LOGITS
     advice
    0.09
    _answers
    0.09
    answers
    0.08
     assistance
    0.08
     troubleshooting
    0.08
     acquainted
    0.08
     सलाह
    0.08
     inquiries
    0.08
    意见
    0.08
    assist
    0.08
    Activations Density 0.003%

    No Known Activations