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. 53793
    Prev
    Next
    INDEX
    Explanations

    quantity and code

    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
     recruit
    -0.07
    orizon
    -0.07
    れ
    -0.07
    inee
    -0.07
    卒
    -0.07
    inees
    -0.07
     Amnesty
    -0.07
     perfil
    -0.07
     recruits
    -0.07
     portal
    -0.06
    POSITIVE LOGITS
     decrement
    0.13
    Increment
    0.13
     Increment
    0.13
    crement
    0.13
    crements
    0.12
     incremental
    0.12
    increment
    0.12
    CREMENT
    0.12
    .increment
    0.12
     increments
    0.12
    Activations Density 0.005%

    No Known Activations