© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113118
    Prev
    Next
    INDEX
    Explanations

    extreme

    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
    habit
    -0.08
     menj
    -0.08
    Hace
    -0.08
    hla
    -0.08
     violence
    -0.08
     Sams
    -0.08
     stream
    -0.08
     Cole
    -0.07
     minhas
    -0.07
     lak
    -0.07
    POSITIVE LOGITS
     extremes
    0.09
     extrema
    0.08
    とな
    0.08
    之一
    0.08
     extrem
    0.08
    І
    0.08
    464
    0.08
     granddaughter
    0.07
    456
    0.07
     potentials
    0.07
    Activations Density 0.004%

    No Known Activations