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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55898
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     docket
    -0.09
     eup
    -0.08
     mismas
    -0.08
     expressly
    -0.08
    iented
    -0.08
     opd
    -0.08
     indemn
    -0.07
     pls
    -0.07
    .Desc
    -0.07
    ศึกษ
    -0.07
    POSITIVE LOGITS
    مث
    0.08
     iconic
    0.08
     тан
    0.08
    (Mockito
    0.08
     ਆ
    0.08
    ازت
    0.08
    恋
    0.08
     खाना
    0.07
    ройки
    0.07
     gang
    0.07
    Activations Density 0.146%

    No Known Activations