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. 119173
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     Schwe
    -0.09
     Leon
    -0.08
     olabilir
    -0.07
    吧
    -0.07
    >>(
    -0.07
    μαι
    -0.07
    GROUND
    -0.07
    >{
    -0.07
    920
    -0.07
    ordinary
    -0.07
    POSITIVE LOGITS
     وكيف
    0.09
     cuándo
    0.08
     حدوث
    0.08
    บ
    0.08
     wann
    0.08
    /how
    0.08
    وقيت
    0.08
     dictated
    0.08
     cuáles
    0.08
     کب
    0.07
    Activations Density 0.040%

    No Known Activations