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. 65888
    Prev
    Next
    INDEX
    Explanations

    plasmids

    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
     حرف
    -0.08
     tentative
    -0.08
     Müll
    -0.08
     æ
    -0.08
     parole
    -0.07
     paw
    -0.07
     swear
    -0.07
     überall
    -0.07
     tent
    -0.07
    禁
    -0.07
    POSITIVE LOGITS
     containing
    0.09
    kering
    0.08
     dataframe
    0.08
     plasm
    0.08
     membrane
    0.08
    Diagram
    0.07
    axis
    0.07
     mère
    0.07
    ring
    0.07
    Daniel
    0.07
    Activations Density 0.002%

    No Known Activations