© 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. 78495
    Prev
    Next
    INDEX
    Explanations

    with

    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
    -mentioned
    -0.09
    FI
    -0.08
     Shu
    -0.08
     Fame
    -0.08
     (=
    -0.08
     المقد
    -0.08
     Employment
    -0.08
    程序集
    -0.08
    Son
    -0.08
    */↵
    -0.08
    POSITIVE LOGITS
     vibrant
    0.10
     unusual
    0.08
     accents
    0.08
    kr
    0.08
     contrasting
    0.08
    �
    0.08
     vivid
    0.08
    营
    0.08
     subtle
    0.07
     disper
    0.07
    Activations Density 0.018%

    No Known Activations