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. 30590
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     alc
    -0.08
     Cop
    -0.08
    ेड
    -0.08
     astonishing
    -0.08
    olph
    -0.07
    岗
    -0.07
     cad
    -0.07
    CID
    -0.07
     importantly
    -0.07
     Ul
    -0.07
    POSITIVE LOGITS
    _mex
    0.08
     Ith
    0.08
     xt
    0.07
     cc
    0.07
    ನ್ನು
    0.07
     DAT
    0.07
     CC
    0.07
    それ
    0.07
     Kru
    0.07
    _AFTER
    0.07
    Activations Density 0.018%

    No Known Activations