© 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. 26116
    Prev
    Next
    INDEX
    Explanations

    Code and configuration snippets

    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
     sympathetic
    -0.09
     Amma
    -0.08
     Arom
    -0.08
     symmetrical
    -0.08
     يصبح
    -0.08
     սկս
    -0.08
     แข
    -0.08
     تجد
    -0.07
    hnt
    -0.07
     العربية
    -0.07
    POSITIVE LOGITS
     interview
    0.08
     forecasts
    0.08
     перег
    0.08
     interviews
    0.07
    .item
    0.07
     Subscription
    0.07
     Fernse
    0.07
    .subscription
    0.07
    111
    0.07
    .met
    0.07
    Activations Density 0.024%

    No Known Activations