© 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. 95647
    Prev
    Next
    INDEX
    Explanations

    receptor-mediated drug delivery

    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
     para
    -0.07
     parsed
    -0.07
     chis
    -0.07
     strengthens
    -0.07
     azalt
    -0.07
     संत
    -0.07
     loud
    -0.07
     blank
    -0.07
     welfare
    -0.07
    เศ
    -0.07
    POSITIVE LOGITS
     доставки
    0.11
     попад
    0.10
     trafficking
    0.10
     uptake
    0.10
     vervoer
    0.10
    Transportation
    0.10
     привлекатель
    0.10
    运输
    0.09
     Transportation
    0.09
     доставка
    0.09
    Activations Density 0.004%

    No Known Activations