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. 19506
    Prev
    Next
    INDEX
    Explanations

    common words and punctuation

    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
     cualquier
    -0.15
     orice
    -0.14
     nenpòt
    -0.13
     qualquer
    -0.13
     ਕੋਈ
    -0.13
     любого
    -0.13
     ಯಾವುದೇ
    -0.13
     anumang
    -0.13
     любой
    -0.13
     any
    -0.12
    POSITIVE LOGITS
     The
    0.13
     (
    0.13
     '
    0.12
    The
    0.12
    **
    0.12
     to
    0.11
    -
    0.11
     the
    0.10
     
    0.10
    :
    0.10
    Activations Density 0.068%

    No Known Activations