© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109835
    Prev
    Next
    INDEX
    Explanations

    应用

    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
    Negative Logits
    �்த
    -0.09
    宅
    -0.08
     Seth
    -0.08
     صاح
    -0.08
    rodk
    -0.08
     mixes
    -0.07
    lade
    -0.07
     misses
    -0.07
     shut
    -0.07
     manque
    -0.07
    POSITIVE LOGITS
    用途
    0.12
    领域
    0.11
     분야
    0.10
     applications
    0.10
     eingesetzt
    0.09
     rộng
    0.09
    广
    0.09
     בתחום
    0.09
    Applications
    0.08
     toepassingen
    0.08
    Activations Density 0.039%

    No Known Activations