© 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. 45576
    Prev
    Next
    INDEX
    Explanations

    Digital Millennium Copyright Act

    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
     Luz
    -0.08
     TODO
    -0.08
     �
    -0.08
     buhay
    -0.08
     dahil
    -0.07
     Plat
    -0.07
     vida
    -0.07
     Riz
    -0.07
    闭
    -0.07
     拉
    -0.07
    POSITIVE LOGITS
     aanzien
    0.08
     بهذا
    0.08
     Apt
    0.07
    /random
    0.07
     desempe
    0.07
    でも
    0.07
     مهم
    0.07
     comparaison
    0.07
    alit
    0.07
    Ori
    0.07
    Activations Density 0.000%

    No Known Activations