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. 12969
    Prev
    Next
    INDEX
    Explanations

    eq

    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
     بھائی
    -0.08
     seg
    -0.08
     banc
    -0.08
     holen
    -0.08
    _FACT
    -0.08
    은행
    -0.08
     steigen
    -0.07
    나는
    -0.07
     mothers
    -0.07
     FAMILY
    -0.07
    POSITIVE LOGITS
    Cancelable
    0.08
    :param
    0.08
     одновременно
    0.07
    (parameters
    0.07
    .Matrix
    0.07
     plum
    0.07
    (map
    0.07
    .Pro
    0.07
     Mission
    0.07
    shore
    0.07
    Activations Density 0.002%

    No Known Activations