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. 19724
    Prev
    Next
    INDEX
    Explanations

    Nonsensical/mixed content

    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
     hectares
    -0.08
     have
    -0.08
     ಅಗ
    -0.08
     moons
    -0.08
    :J
    -0.08
     provavelmente
    -0.08
    ಿಗಳನ್ನು
    -0.08
     quarters
    -0.07
    Optim
    -0.07
    :↵↵
    -0.07
    POSITIVE LOGITS
     Certain
    0.09
     Some
    0.08
    Certain
    0.08
    olola
    0.08
    ikaʻi
    0.08
    ��
    0.08
     Nong
    0.08
     Naruto
    0.08
     dorp
    0.08
     действие
    0.07
    Activations Density 0.030%

    No Known Activations