© 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. 99490
    Prev
    Next
    INDEX
    Explanations

    crowdedness

    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
     agrade
    -0.08
    .capitalize
    -0.08
     Sab
    -0.08
    .mouse
    -0.08
    aww
    -0.08
    iket
    -0.07
    лит
    -0.07
    pard
    -0.07
     Mél
    -0.07
     longtime
    -0.07
    POSITIVE LOGITS
     torno
    0.09
     вокруг
    0.09
     occupation
    0.08
     commod
    0.08
     waterways
    0.08
    /conf
    0.08
     banget
    0.08
    -packed
    0.07
    -around
    0.07
     Commod
    0.07
    Activations Density 0.010%

    No Known Activations