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. 30580
    Prev
    Next
    INDEX
    Explanations

    set function

    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
     arbit
    -0.08
     Mata
    -0.07
     Wing
    -0.07
     przy
    -0.07
    "_
    -0.07
    一种
    -0.07
     War
    -0.07
    asjon
    -0.07
    _WE
    -0.07
     monarch
    -0.07
    POSITIVE LOGITS
    上述
    0.09
     που
    0.09
     newcomer
    0.08
    τές
    0.08
    োজন
    0.08
     Randy
    0.08
     aforementioned
    0.07
    above
    0.07
     αυτές
    0.07
    ④
    0.07
    Activations Density 0.062%

    No Known Activations