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. 41954
    Prev
    Next
    INDEX
    Explanations

    ance

    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
     stretch
    -0.08
    chnung
    -0.08
     chọn
    -0.08
    emaking
    -0.08
     défic
    -0.08
     leafy
    -0.08
    ائز
    -0.07
    Modifiers
    -0.07
     sturd
    -0.07
     lenders
    -0.07
    POSITIVE LOGITS
    _utils
    0.08
    515
    0.08
    _prod
    0.08
    .Web
    0.08
    /utils
    0.07
    .iteritems
    0.07
    .download
    0.07
    .client
    0.07
    _web
    0.07
     అ
    0.07
    Activations Density 0.006%

    No Known Activations