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. 11-RESID-POST-AA
    6. 60383
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    stice
    -0.10
     gummy
    -0.09
     gummies
    -0.09
     irin
    -0.09
    opoly
    -0.09
    .poly
    -0.08
     Fourier
    -0.08
     Invisalign
    -0.08
    -poly
    -0.08
     stats
    -0.08
    POSITIVE LOGITS
     Test
    0.11
    Test
    0.11
    步骤
    0.11
    .Test
    0.10
     test
    0.10
     procedimento
    0.09
     steps
    0.09
    测试
    0.09
    Steps
    0.09
     કાર્યવાહી
    0.09
    Activations Density 0.004%

    No Known Activations