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. 27619
    Prev
    Next
    INDEX
    Explanations

    proposing or clarifying

    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
     incarceration
    -0.08
     degrees
    -0.08
    Degrees
    -0.08
     termination
    -0.08
    .mozilla
    -0.07
     acquaintance
    -0.07
     friend's
    -0.07
     чуж
    -0.07
    nego
    -0.07
     minded
    -0.07
    POSITIVE LOGITS
    习近平
    0.13
     강조
    0.11
     говорится
    0.11
    强调
    0.11
     emphasized
    0.10
     أهمية
    0.10
    贯彻
    0.10
    (theme
    0.09
    党建
    0.09
    新时代
    0.09
    Activations Density 0.015%

    No Known Activations