Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11699
    Prev
    Next
    INDEX
    Explanations

    ades

    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
    经典
    -0.08
     adrenaline
    -0.07
     acrylic
    -0.07
     ak
    -0.07
    abl
    -0.07
     кад
    -0.07
     Baba
    -0.07
     ndër
    -0.07
     darr
    -0.07
    激情
    -0.07
    POSITIVE LOGITS
    واره
    0.09
    .Restr
    0.08
    ltal
    0.07
    strom
    0.07
    uchtet
    0.07
     cyn
    0.07
    _REALTYPE
    0.07
    nehin
    0.07
     đo
    0.07
    _ratio
    0.07
    Activations Density 0.003%

    No Known Activations