© 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. 79532
    Prev
    Next
    INDEX
    Explanations

    much

    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
     siège
    -0.08
     tid
    -0.08
     LPARAM
    -0.08
     கால
    -0.08
    bies
    -0.07
    lihat
    -0.07
     σύ
    -0.07
     пери
    -0.07
    tid
    -0.07
     сведения
    -0.07
    POSITIVE LOGITS
     hitting
    0.07
     gete
    0.07
    Runs
    0.07
     luck
    0.07
    _runs
    0.07
     nanop
    0.07
     لل
    0.07
     interviewing
    0.07
     kand
    0.07
    তো
    0.07
    Activations Density 0.006%

    No Known Activations