© 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. 50739
    Prev
    Next
    INDEX
    Explanations

    B

    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
     saja
    -0.08
     clues
    -0.08
    افات
    -0.08
     taus
    -0.08
     Starter
    -0.08
     ..↵
    -0.08
     themes
    -0.08
    ատ
    -0.08
     ..↵↵
    -0.08
     Marino
    -0.08
    POSITIVE LOGITS
    ey
    0.11
    eyi
    0.09
    ritt
    0.09
    is
    0.09
    iyi
    0.08
    achelorette
    0.08
    ising
    0.08
    TS
    0.08
    ecs
    0.08
     extremamente
    0.08
    Activations Density 0.001%

    No Known Activations