© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 52122
    Prev
    Next
    INDEX
    Explanations

    Route

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    roof
    -0.10
    ruits
    -0.09
    🏻
    -0.09
    ström
    -0.08
    Roof
    -0.08
    riors
    -0.08
    rate
    -0.08
     আন্দোল
    -0.08
    rooms
    -0.08
    ihat
    -0.08
    POSITIVE LOGITS
    planner
    0.14
    Planner
    0.13
     planner
    0.13
    规划
    0.13
     planners
    0.12
     Planner
    0.12
    /path
    0.11
    Planning
    0.11
     planning
    0.11
    planung
    0.11
    Activations Density 0.026%

    No Known Activations