Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43933
    Prev
    Next
    INDEX
    Explanations

    Russian, innervations

    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
    ennes
    -0.09
    iaux
    -0.08
    _escape
    -0.08
     completos
    -0.08
    áis
    -0.08
    ání
    -0.08
    nem
    -0.08
    rique
    -0.07
    enciais
    -0.07
     Benn
    -0.07
    POSITIVE LOGITS
     attaches
    0.10
     attaching
    0.10
     plantar
    0.09
     Kontakte
    0.09
    .Attach
    0.09
     attachments
    0.09
     wiring
    0.09
     연결
    0.08
    _attach
    0.08
    .attach
    0.08
    Activations Density 0.008%

    No Known Activations