Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11790
    Prev
    Next
    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash

    It detects mentions of command-line commands and running commands (instructions for invoking processes or concurrently running tasks).

    oai_token-act-pair · gpt-5-miniTriggered by @mlfinancebook

    command-line usage syntax—especially flags, options, parameters, and code-like tokens in technical documentation contexts.

    oai_token-act-pair · gpt-5Triggered by @tatsatx
    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
     Sent
    -0.08
    困难
    -0.08
     Colonial
    -0.08
     Rural
    -0.08
     sanitation
    -0.08
     �
    -0.08
    	Product
    -0.08
    -Version
    -0.07
     Solar
    -0.07
    emu
    -0.07
    POSITIVE LOGITS
     exit
    0.08
     very
    0.07
     fou
    0.07
     dudes
    0.07
     trace
    0.07
    checkpoint
    0.07
     magn
    0.07
     olunan
    0.07
     그대로
    0.07
    เรา
    0.07
    Activations Density 0.000%

    No Known Activations