© 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. 50315
    Prev
    Next
    INDEX
    Explanations

    ét

    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
    iteach
    -0.09
    ite
    -0.08
    िट
    -0.08
    итан
    -0.08
    ит
    -0.08
    ाइएको
    -0.08
    ’honneur
    -0.08
     Shan
    -0.07
    ம்ம
    -0.07
     litig
    -0.07
    POSITIVE LOGITS
     centr
    0.09
     중심
    0.08
    센터
    0.08
    centr
    0.08
    sø
    0.08
     여행
    0.07
    ncpy
    0.07
    rese
    0.07
    cen
    0.07
     centros
    0.07
    Activations Density 0.001%

    No Known Activations