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. 23157
    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
    IMER
    -0.08
     MLS
    -0.08
     gostar
    -0.07
    元
    -0.07
    $text
    -0.07
     Surveillance
    -0.07
    附件
    -0.07
     안내
    -0.07
    imer
    -0.07
    .withdraw
    -0.07
    POSITIVE LOGITS
     Pav
    0.08
     pued
    0.08
     count
    0.08
    inių
    0.07
    ेंद्र
    0.07
     powering
    0.07
     تاثیر
    0.07
     trading
    0.07
     hvis
    0.07
     بدل
    0.07
    Activations Density 0.006%

    No Known Activations