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. 59813
    Prev
    Next
    INDEX
    Explanations

    11

    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
    ferenced
    -0.08
    Transparency
    -0.08
    -acre
    -0.08
     begitu
    -0.08
    -transparent
    -0.07
    äksi
    -0.07
    -funded
    -0.07
    phan
    -0.07
     pesado
    -0.07
     violência
    -0.07
    POSITIVE LOGITS
     ruled
    0.08
    .grid
    0.08
     Kemp
    0.08
     grid
    0.08
    貌
    0.08
     pip
    0.08
     Professional
    0.07
     cortical
    0.07
    Grid
    0.07
     logarith
    0.07
    Activations Density 0.001%

    No Known Activations