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. 42041
    Prev
    Next
    INDEX
    Explanations

    Fit, suits, fashion

    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
    -0.08
     hjelp
    -0.07
    enga
    -0.07
     include
    -0.07
     downloads
    -0.07
     documentation
    -0.07
     cập
    -0.07
    .asc
    -0.07
     mua
    -0.07
    .gs
    -0.07
    POSITIVE LOGITS
     suitability
    0.14
     suited
    0.13
     cocok
    0.12
     uyğun
    0.12
     geeignet
    0.12
     hästi
    0.11
    Suit
    0.11
     uitstekend
    0.11
     snug
    0.11
     hervorragend
    0.10
    Activations Density 0.088%

    No Known Activations