© 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. 91718
    Prev
    Next
    INDEX
    Explanations

    cell viability assays

    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
     kih
    -0.09
     eccles
    -0.08
    Orders
    -0.08
    -0.08
     tek
    -0.07
     capo
    -0.07
     GOVERN
    -0.07
    公共
    -0.07
    ваз
    -0.07
     nozzle
    -0.07
    POSITIVE LOGITS
     viability
    0.14
     viable
    0.11
     assessments
    0.10
     Assessment
    0.10
     toxicity
    0.10
     survival
    0.09
     apopt
    0.09
     assessment
    0.09
     Bewert
    0.09
     happiness
    0.09
    Activations Density 0.002%
    No Known Activations