© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 108121
    Prev
    Next
    INDEX
    Explanations

    fluency

    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
     cradle
    -0.08
     présent
    -0.07
     patterned
    -0.07
    520
    -0.07
    ️⃣
    -0.07
    -0.07
    Benjamin
    -0.07
    =u
    -0.07
     William
    -0.07
    .payload
    -0.07
    POSITIVE LOGITS
     spe
    0.08
     versed
    0.07
    NESS
    0.07
     tur
    0.07
     akt
    0.07
    活
    0.07
     attainable
    0.07
     жыл
    0.07
    있
    0.07
    ness
    0.07
    Activations Density 0.006%
    No Known Activations