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. 12074
    Prev
    Next
    INDEX
    Explanations

    bike sharing

    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
     lån
    -0.08
     LTD
    -0.07
     extension
    -0.07
     känner
    -0.07
    ですよ
    -0.07
     ziet
    -0.07
    reu
    -0.07
    wissen
    -0.07
     kindle
    -0.07
     beginnt
    -0.07
    POSITIVE LOGITS
    .population
    0.08
     Portfolio
    0.08
    )sender
    0.08
    [column
    0.08
     portfolio
    0.08
    acks
    0.08
    [parent
    0.07
     Fixture
    0.07
     Bug
    0.07
     Preconditions
    0.07
    Activations Density 0.001%

    No Known Activations