Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19549
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Somehow
    -0.11
     irgendwie
    -0.11
    (?)
    -0.10
    .some
    -0.10
     irgende
    -0.10
     qualche
    -0.10
     scheint
    -0.10
     કંઈ
    -0.10
    Нек
    -0.10
    몇
    -0.10
    POSITIVE LOGITS
     "
    0.10
     https
    0.10
     a
    0.09
     not
    0.09
     both
    0.09
     ↵↵
    0.09
     '
    0.09
     the
    0.09
     being
    0.09
     e
    0.08
    Activations Density 0.059%

    No Known Activations