© 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. 99713
    Prev
    Next
    INDEX
    Explanations

    capitalization

    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
    购买
    -0.09
     رز
    -0.08
     વીડિયો
    -0.08
    顾
    -0.08
     comprador
    -0.08
    ilios
    -0.08
     mochila
    -0.08
     Batu
    -0.08
     σπίτι
    -0.08
     vivienda
    -0.08
    POSITIVE LOGITS
     uppercase
    0.16
    uppercase
    0.14
     strtoupper
    0.14
     shouted
    0.12
     bold
    0.11
    -uppercase
    0.11
     shouting
    0.11
     lowercase
    0.11
     CAPITAL
    0.11
    .upper
    0.11
    Activations Density 0.022%

    No Known Activations