© 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. 45748
    Prev
    Next
    INDEX
    Explanations

    fraction of normal value

    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
    ત્ર
    -0.07
    -learning
    -0.07
    Ontology
    -0.07
    Gov
    -0.06
     crimson
    -0.06
     ಜನ
    -0.06
     simulations
    -0.06
     demographics
    -0.06
    firm
    -0.06
     izao
    -0.06
    POSITIVE LOGITS
     encontrada
    0.09
     të
    0.09
    正常
    0.09
     bah
    0.09
     encontrado
    0.09
     référence
    0.09
    lal
    0.08
     Norm
    0.08
     nò
    0.08
     trovato
    0.08
    Activations Density 0.050%

    No Known Activations