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. 77316
    Prev
    Next
    INDEX
    Explanations

    Commas

    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
    iden
    -0.09
    .TRAILING
    -0.08
     loyalty
    -0.08
    lev
    -0.07
    Burger
    -0.07
    quare
    -0.07
     sau
    -0.07
     award
    -0.07
    .trailing
    -0.07
     Burger
    -0.07
    POSITIVE LOGITS
     查询
    0.08
     Calder
    0.08
    alarda
    0.08
    tedy
    0.08
    查询
    0.07
     ihtiyaç
    0.07
     urgence
    0.07
     ddiwedd
    0.07
    künfte
    0.07
     unsett
    0.07
    Activations Density 0.001%

    No Known Activations