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. 75891
    Prev
    Next
    INDEX
    Explanations

    Number of divisors

    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
    logos
    -0.08
    úe
    -0.08
     asociaciones
    -0.08
    орах
    -0.08
    лого
    -0.08
     culturales
    -0.08
    spart
    -0.08
    sprecher
    -0.08
    kere
    -0.07
     preferência
    -0.07
    POSITIVE LOGITS
     म्हणजे
    0.09
    ercise
    0.08
    -tier
    0.08
    -ब
    0.07
     enda
    0.07
     Dolphin
    0.07
    510
    0.07
     ddl
    0.07
     ಸರ
    0.07
    erta
    0.07
    Activations Density 0.009%

    No Known Activations