© 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. 111231
    Prev
    Next
    INDEX
    Explanations

    letter "h"

    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
     Mart
    -0.08
     geb
    -0.08
     mentira
    -0.08
     condensed
    -0.08
    铺
    -0.07
     marts
    -0.07
     compressors
    -0.07
    恒
    -0.07
     prisión
    -0.07
     cold
    -0.07
    POSITIVE LOGITS
     پ
    0.09
    pegawai
    0.09
    drag
    0.08
     कप्त
    0.08
    ̊
    0.08
    inyin
    0.08
    Sometimes
    0.08
     Elektro
    0.07
    ýt
    0.07
     FW
    0.07
    Activations Density 0.004%

    No Known Activations