© 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. 94632
    Prev
    Next
    INDEX
    Explanations

    review

    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
     trousers
    -0.08
     лев
    -0.08
     grape
    -0.08
    iah
    -0.07
     boots
    -0.07
    ainty
    -0.07
    gb
    -0.07
     approximately
    -0.07
    GB
    -0.07
     Grid
    -0.07
    POSITIVE LOGITS
    报道
    0.09
     Ejecutivo
    0.08
    览
    0.08
     literature
    0.08
    揭秘
    0.08
     beschäftigen
    0.08
    发表
    0.08
     литера
    0.08
     recopil
    0.08
    この記事
    0.08
    Activations Density 0.010%

    No Known Activations