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. 23-RESID-POST-AA
    6. 97063
    Prev
    Next
    INDEX
    Explanations

    qqu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нен
    -0.09
     Änder
    -0.09
     envisage
    -0.08
    VAC
    -0.08
    agiye
    -0.08
    ماع
    -0.08
     نشده
    -0.08
     mudou
    -0.08
    Func
    -0.08
     搜
    -0.08
    POSITIVE LOGITS
     p
    0.08
    ad
    0.08
     꾸
    0.08
    oms
    0.08
     a
    0.08
    .books
    0.08
     X
    0.08
     +
    0.07
    .firstname
    0.07
     대학
    0.07
    Activations Density 0.003%

    No Known Activations