© 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. 44756
    Prev
    Next
    INDEX
    Explanations

    =

    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
     esport
    -0.08
     électronique
    -0.08
     nonsense
    -0.08
    nus
    -0.08
     partid
    -0.07
    nir
    -0.07
     konden
    -0.07
    oyle
    -0.07
     huk
    -0.07
     Saf
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.09
    _Size
    0.08
     உறுப்ப
    0.08
    connections
    0.08
     ervaringen
    0.07
    进行了
    0.07
     проведения
    0.07
    0.07
     относятся
    0.07
     threads
    0.07
    Activations Density 0.009%

    No Known Activations