© 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. 7666
    Prev
    Next
    INDEX
    Explanations

    to

    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
     roupa
    -0.08
     age
    -0.08
     idade
    -0.08
     portug
    -0.08
    enis
    -0.07
    Mex
    -0.07
     retirada
    -0.07
     মতো
    -0.07
     utensils
    -0.07
     kleding
    -0.07
    POSITIVE LOGITS
     vastly
    0.08
     alot
    0.08
     VERY
    0.08
    जान
    0.08
     Shares
    0.08
     无限
    0.08
     Vast
    0.08
    Faces
    0.07
    faces
    0.07
    ointed
    0.07
    Activations Density 0.001%

    No Known Activations