© 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. 26031
    Prev
    Next
    INDEX
    Explanations

    functional programming, classes

    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
     pigment
    -0.08
     Dalton
    -0.08
    -0.08
     فرض
    -0.08
     authoritative
    -0.08
     infest
    -0.08
     masses
    -0.08
     Archae
    -0.07
    Mass
    -0.07
    Bil
    -0.07
    POSITIVE LOGITS
     Callable
    0.13
     Runnable
    0.12
    .callback
    0.12
    	callback
    0.12
    callback
    0.11
    _callable
    0.11
    anonymous
    0.11
     callbacks
    0.11
     callback
    0.11
     Callback
    0.11
    Activations Density 0.012%
    No Known Activations