© 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. 79394
    Prev
    Next
    INDEX
    Explanations

    million

    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
    零钱
    -0.08
    ವ
    -0.08
    Preparing
    -0.08
     Preparing
    -0.08
     resolving
    -0.08
     Walgreens
    -0.07
    -0.07
     prepping
    -0.07
    Cash
    -0.07
    付款
    -0.07
    POSITIVE LOGITS
     kilometers
    0.11
     kilometres
    0.10
     hectare
    0.10
     lakes
    0.10
     geograf
    0.09
     scenic
    0.09
     carretera
    0.09
     kilomètres
    0.09
     roads
    0.09
     kilomet
    0.09
    Activations Density 0.024%
    No Known Activations