© 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. 69948
    Prev
    Next
    INDEX
    Explanations

    利

    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
     von
    -0.09
     музы
    -0.08
     explos
    -0.08
     Angriff
    -0.08
     называют
    -0.08
     vigilance
    -0.08
    カル
    -0.08
     болез
    -0.08
    modus
    -0.08
     Advoc
    -0.08
    POSITIVE LOGITS
    ces
    0.09
     ide
    0.08
    添
    0.08
     ích
    0.08
     المرج
    0.07
     tip
    0.07
    zd
    0.07
    yl
    0.07
    ‘y
    0.07
     waiver
    0.07
    Activations Density 0.001%

    No Known Activations