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. 111855
    Prev
    Next
    INDEX
    Explanations

    import

    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
     appropr
    -0.08
     BOT
    -0.08
     FONT
    -0.08
     sepak
    -0.08
    と
    -0.07
    ை
    -0.07
     DATABASE
    -0.07
     DON
    -0.07
    ుణ
    -0.07
     kolej
    -0.07
    POSITIVE LOGITS
     responsabilité
    0.08
    .Globalization
    0.08
     opiniões
    0.08
    "encoding
    0.07
    .nio
    0.07
    .geometry
    0.07
     responsabilidade
    0.07
     responsabilités
    0.07
    "fmt
    0.07
    .IOException
    0.07
    Activations Density 0.004%

    No Known Activations