© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45558
    Prev
    Next
    INDEX
    Explanations

    v

    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
     poprzez
    -0.08
     adres
    -0.07
    GES
    -0.07
    ges
    -0.07
     crease
    -0.07
    bord
    -0.07
     Rund
    -0.07
    han
    -0.07
    seat
    -0.07
    &quot
    -0.07
    POSITIVE LOGITS
     ต้อง
    0.08
     چھ
    0.08
     ご
    0.08
     Supplements
    0.07
    aty
    0.07
     fileprivate
    0.07
     mfe
    0.07
     hotels
    0.07
     gout
    0.07
     "%"↵
    0.07
    Activations Density 0.003%

    No Known Activations