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. 120386
    Prev
    Next
    INDEX
    Explanations

    subdomains

    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
    wir
    -0.08
    go
    -0.08
     wander
    -0.08
    ovski
    -0.08
     go
    -0.08
    Omega
    -0.07
    Td
    -0.07
     vermittelt
    -0.07
    _mb
    -0.07
     tup
    -0.07
    POSITIVE LOGITS
    /Sub
    0.08
    /ac
    0.08
     ਪ੍ਰ
    0.08
    /sub
    0.08
     التابعة
    0.08
     Eis
    0.08
     फी
    0.08
    aven
    0.07
     fech
    0.07
     namespaces
    0.07
    Activations Density 0.002%

    No Known Activations