© 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 EvalsExportsinterp-engineNEWAPI 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. 111266
    Prev
    Next
    INDEX
    Explanations

    hair

    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
     alcool
    -0.08
    cribes
    -0.07
     lagu
    -0.07
     भुग
    -0.07
     음
    -0.07
    incia
    -0.07
    上一
    -0.07
     ingrédients
    -0.07
     feeling
    -0.07
    েছি
    -0.07
    POSITIVE LOGITS
     hij
    0.08
    Hij
    0.08
    (paths
    0.08
     Hij
    0.07
    .Visibility
    0.07
    (lo
    0.07
    (hw
    0.07
     Cort
    0.07
    .Cast
    0.07
    ло
    0.07
    Activations Density 0.004%

    No Known Activations