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. 55955
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
    .plus
    -0.08
    .stroke
    -0.08
     querida
    -0.07
    etto
    -0.07
    dd
    -0.07
     vermitteln
    -0.07
     glitch
    -0.07
    .shift
    -0.07
     NS
    -0.07
    ucumber
    -0.07
    POSITIVE LOGITS
     crít
    0.11
    思
    0.11
     pensamiento
    0.11
     pensamento
    0.11
    -thinking
    0.11
     aware
    0.11
    Akt
    0.10
     questioning
    0.10
     minds
    0.10
     Akt
    0.10
    Activations Density 0.013%

    No Known Activations