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

    Neuronpedia

    APICircuit 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. 75938
    Prev
    Next
    INDEX
    Explanations

    Actions and states of people

    np_max-act · gemini-2.0-flash

    beginnings of documents, especially the special start-of-text marker indicating a new text segment.

    oai_token-act-pair · gpt-5Triggered by @tatsatx

    It strongly detects the special start-of-text / start-of-sequence token (the <|startoftext|> marker).

    oai_token-act-pair · gpt-5-miniTriggered 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
    USER
    -0.08
    rud
    -0.07
    _DOM
    -0.07
     ಅನ್ನು
    -0.07
     танд
    -0.07
    _T
    -0.07
     ausz
    -0.07
    DOM
    -0.07
     therapeutic
    -0.07
     Nicholson
    -0.07
    POSITIVE LOGITS
     അവരുടെ
    0.10
    -ils
    0.09
     తమ
    0.09
     själva
    0.09
     ತಮ್ಮ
    0.09
     الذين
    0.09
    :innen
    0.09
     salaries
    0.08
     তাঁদের
    0.08
     whisper
    0.08
    Activations Density 0.465%

    No Known Activations