© 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. 95472
    Prev
    Next
    INDEX
    Explanations

    ategy

    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
    Egypt
    -0.09
    τό
    -0.08
    بطال
    -0.08
    enticated
    -0.08
     nearly
    -0.08
    kening
    -0.07
    veli
    -0.07
    associated
    -0.07
     trakt
    -0.07
    =p
    -0.07
    POSITIVE LOGITS
     fluctuate
    0.08
     Operations
    0.08
     fal
    0.08
     AI
    0.07
     Angaben
    0.07
     (($
    0.07
     साबित
    0.07
     operaciones
    0.07
     bzw
    0.07
     lips
    0.07
    Activations Density 0.001%

    No Known Activations