© 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. 99531
    Prev
    Next
    INDEX
    Explanations

    econometrics

    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
     quilting
    -0.09
     نصف
    -0.08
     Foods
    -0.08
     tegenover
    -0.08
    코
    -0.08
    .social
    -0.08
     muze
    -0.08
     nepot
    -0.08
    -0.08
     twee
    -0.08
    POSITIVE LOGITS
    acid
    0.09
     phosphory
    0.08
     والتح
    0.08
    ermann
    0.08
     Spart
    0.08
     dissolution
    0.08
     acid
    0.07
    Poly
    0.07
     recher
    0.07
    inite
    0.07
    Activations Density 0.002%
    No Known Activations