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

    Neuronpedia

    Jacobian LensNEW
    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. 112568
    Prev
    Next
    INDEX
    Explanations

    them

    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
     quickest
    -0.08
     объекта
    -0.08
     presentation
    -0.07
     portrayed
    -0.07
     biochemical
    -0.07
     Reserv
    -0.07
     Представ
    -0.07
    Statistics
    -0.07
     owner
    -0.07
     Louisiana
    -0.07
    POSITIVE LOGITS
    鞋
    0.16
     shoes
    0.16
     sneakers
    0.15
     chaussures
    0.15
     sandals
    0.15
     Schuhe
    0.15
     schoenen
    0.14
     обув
    0.14
     footwear
    0.14
     ruedas
    0.13
    Activations Density 0.132%

    No Known Activations