© 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. 54337
    Prev
    Next
    INDEX
    Explanations

    alpha

    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
    lụ
    -0.08
     ARC
    -0.08
    Triangle
    -0.08
    'elles
    -0.07
     Skeleton
    -0.07
    Thumbnail
    -0.07
    .ALIGN
    -0.07
    .Side
    -0.07
     arcs
    -0.07
     Triangle
    -0.07
    POSITIVE LOGITS
    akhi
    0.08
     இருந்த
    0.08
     прояв
    0.08
     پری
    0.07
     Telecom
    0.07
    톡
    0.07
     tele
    0.07
    šina
    0.07
     Tele
    0.07
     Kathmandu
    0.07
    Activations Density 0.000%

    No Known Activations