© 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. 114098
    Prev
    Next
    INDEX
    Explanations

    ние

    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
     पाह
    -0.08
     impro
    -0.08
     आनंद
    -0.07
     disag
    -0.07
     evalu
    -0.07
    oraj
    -0.07
    virt
    -0.07
     seen
    -0.07
    pliant
    -0.07
    ysta
    -0.07
    POSITIVE LOGITS
     nights
    0.11
     evenings
    0.11
     noches
    0.09
    尸
    0.09
     kveld
    0.09
    ратите
    0.08
     nightlife
    0.08
     noites
    0.08
    晚上
    0.08
    ruary
    0.08
    Activations Density 0.013%

    No Known Activations