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. 78549
    Prev
    Next
    INDEX
    Explanations

    code/configurations

    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
     hê
    -0.08
    人
    -0.08
    ombie
    -0.08
     Elliott
    -0.08
    Aer
    -0.08
    福利彩票
    -0.08
     një
    -0.08
     spirit
    -0.08
     vibes
    -0.07
     embryo
    -0.07
    POSITIVE LOGITS
     фикс
    0.07
     concent
    0.07
     buffered
    0.07
     floors
    0.07
     Which
    0.07
     MED
    0.07
    Prior
    0.07
     ################################
    0.07
     Plug
    0.07
     LOT
    0.07
    Activations Density 0.116%

    No Known Activations