© 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. 23-RESID-POST-AA
    11. 50750
    Prev
    Next
    INDEX
    Explanations

    Data extraction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scss
    -0.07
     function
    -0.07
     granted
    -0.07
    adan
    -0.07
    自动
    -0.07
    aw
    -0.07
     neighborhood
    -0.07
     scheduling
    -0.07
     automatically
    -0.07
    函数
    -0.07
    POSITIVE LOGITS
    undi
    0.08
     развитие
    0.08
     משחק
    0.08
     ardh
    0.08
    戲
    0.08
     timbang
    0.08
     Mato
    0.08
    プリ
    0.08
    arti
    0.08
    nye
    0.08
    Activations Density 0.000%

    No Known Activations