© 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. 3-RESID-POST-AA
    11. 3051
    Prev
    Next
    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regulations
    -0.08
     pe
    -0.07
    aneously
    -0.07
     प्रण
    -0.07
    Ди
    -0.07
     şah
    -0.07
     أسر
    -0.07
     servo
    -0.07
    iate
    -0.07
     märk
    -0.07
    POSITIVE LOGITS
     ausprob
    0.08
     spouse
    0.08
     всі
    0.08
     implanted
    0.08
    pkg
    0.08
     ની
    0.07
    $email
    0.07
     Að
    0.07
     appliquer
    0.07
    @mail
    0.07
    Activations Density 0.000%

    No Known Activations