© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29496
    Prev
    Next
    INDEX
    Explanations

    citations, attribute, rendering

    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
     alak
    -0.08
    isti
    -0.08
     wonder
    -0.07
    征
    -0.07
     soporte
    -0.07
     FILTER
    -0.07
    신
    -0.07
     filters
    -0.07
     declare
    -0.07
     ms
    -0.07
    POSITIVE LOGITS
     Cup
    0.09
     Aboriginal
    0.08
     sā
    0.08
    ierend
    0.08
    reetings
    0.08
     Australian
    0.08
     satan
    0.08
    puter
    0.07
     cup
    0.07
    )..
    0.07
    Activations Density 0.000%

    No Known Activations