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. 113846
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     household
    -0.08
    .callbacks
    -0.07
     webhook
    -0.07
     neo
    -0.07
    .mac
    -0.07
     eyesight
    -0.07
    [curr
    -0.07
    VED
    -0.07
     Rep
    -0.07
     lin
    -0.07
    POSITIVE LOGITS
     Spani
    0.08
    Bold
    0.08
     आराम
    0.08
     naman
    0.08
    comb
    0.08
    꿈
    0.08
     też
    0.07
     Saskatchewan
    0.07
     बज
    0.07
     sharpen
    0.07
    Activations Density 0.026%

    No Known Activations