© 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. 29247
    Prev
    Next
    INDEX
    Explanations

    Computer science/data

    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
    urr
    -0.08
     dom
    -0.08
    utm
    -0.07
     motivations
    -0.07
     vezi
    -0.07
     güçlü
    -0.07
    akis
    -0.07
     mos
    -0.07
     öffentlichen
    -0.07
    ınt
    -0.07
    POSITIVE LOGITS
     encoded
    0.10
     алыш
    0.09
     элементы
    0.09
     scramble
    0.08
     эш
    0.08
     almacenar
    0.08
     conveyed
    0.08
     ал
    0.08
    encoded
    0.08
    _encoded
    0.08
    Activations Density 0.024%

    No Known Activations