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. 7-RESID-POST-AA
    6. 131001
    Prev
    Next
    INDEX
    Explanations

    Telomere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KN
    -0.08
     təs
    -0.08
     tätig
    -0.07
     gericht
    -0.07
     ಎಂದು
    -0.07
     atm
    -0.07
     qualifier
    -0.07
     patience
    -0.07
     себе
    -0.07
    ને
    -0.07
    POSITIVE LOGITS
     Rentals
    0.08
    iern
    0.08
     Seng
    0.08
     Hell
    0.08
     Pale
    0.08
     Asus
    0.08
     chim
    0.08
     Chees
    0.08
     Bah
    0.08
     Aman
    0.08
    Activations Density 0.000%

    No Known Activations