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. 9018
    Prev
    Next
    INDEX
    Explanations

    punctuation, plus sign

    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
    .I
    -0.08
     anchor
    -0.08
     inhabit
    -0.08
     modifying
    -0.08
    .anchor
    -0.08
     beneficiary
    -0.07
    Anchor
    -0.07
     desapar
    -0.07
     different
    -0.07
    anchor
    -0.07
    POSITIVE LOGITS
     ноут
    0.10
     لإ
    0.09
     expedited
    0.08
     электро
    0.08
    _RATE
    0.08
     handmade
    0.08
     tráfico
    0.08
     쇼
    0.08
     Nếu
    0.08
     నగ
    0.08
    Activations Density 0.003%

    No Known Activations