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. 43639
    Prev
    Next
    INDEX
    Explanations

    journaling reflection

    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
     wh
    -0.08
     ಸ್ಥಾನ
    -0.08
    -0.08
     wei
    -0.07
     frac
    -0.07
     wem
    -0.07
    ponenten
    -0.07
     निवासी
    -0.07
     deme
    -0.07
     Code
    -0.07
    POSITIVE LOGITS
     hábito
    0.10
     subconscious
    0.10
     hindsight
    0.10
    Forgot
    0.09
     накоп
    0.09
    累计
    0.09
     acumul
    0.09
     sentimental
    0.09
    -average
    0.09
     scrapbook
    0.09
    Activations Density 0.028%

    No Known Activations