© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8114
    Prev
    Next
    INDEX
    Explanations

    Uber

    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
     Warner
    -0.08
     pumpkins
    -0.08
    اران
    -0.08
     Ons
    -0.08
    לים
    -0.08
    SPD
    -0.08
    دين
    -0.07
     duct
    -0.07
     Reel
    -0.07
     William
    -0.07
    POSITIVE LOGITS
     Muz
    0.08
    event
    0.08
    ee
    0.08
    Mn
    0.08
     entren
    0.08
     Chen
    0.08
    router
    0.07
    Chen
    0.07
    $$
    0.07
     mors
    0.07
    Activations Density 0.004%

    No Known Activations