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. 43982
    Prev
    Next
    INDEX
    Explanations

    об

    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
    ments
    -0.08
     bop
    -0.08
     Merry
    -0.08
    말
    -0.08
    rola
    -0.08
     Coral
    -0.08
    plib
    -0.07
     Schon
    -0.07
    Phone
    -0.07
     આસ
    -0.07
    POSITIVE LOGITS
     screening
    0.09
     تقديم
    0.09
    穿
    0.08
    彻
    0.08
     permeability
    0.08
     Screening
    0.08
     kre
    0.08
    ひ
    0.08
    éo
    0.07
    lens
    0.07
    Activations Density 0.018%

    No Known Activations