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. 30650
    Prev
    Next
    INDEX
    Explanations

    code and file formats

    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
     Pey
    -0.09
     geothermal
    -0.08
    显
    -0.08
     Pinot
    -0.08
     demostrado
    -0.08
     neb
    -0.08
     revival
    -0.07
     Stark
    -0.07
     securities
    -0.07
     refug
    -0.07
    POSITIVE LOGITS
    Guys
    0.08
     spl
    0.08
     dauern
    0.08
     lame
    0.07
     연
    0.07
     kinda
    0.07
    .Assert
    0.07
     acontecer
    0.07
    æði
    0.07
     dessas
    0.07
    Activations Density 0.017%

    No Known Activations