© 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. 44511
    Prev
    Next
    INDEX
    Explanations

    aeration and bubbles

    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
    .Params
    -0.09
     electives
    -0.09
     сярэд
    -0.09
     yek
    -0.08
    retched
    -0.08
    .href
    -0.08
    काल
    -0.08
    graduate
    -0.08
    wann
    -0.08
    Params
    -0.07
    POSITIVE LOGITS
     bubbles
    0.09
    粒
    0.09
     раствор
    0.08
     chl
    0.08
     champagne
    0.08
     litig
    0.08
    atm
    0.07
     turbulence
    0.07
     gey
    0.07
     scav
    0.07
    Activations Density 0.009%

    No Known Activations