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. 46237
    Prev
    Next
    INDEX
    Explanations

    Set theory

    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
     чуть
    -0.09
    赛
    -0.08
     �
    -0.08
     rigs
    -0.08
     rival
    -0.08
     inches
    -0.08
     ügy
    -0.08
    倍率
    -0.08
    秘诀
    -0.08
     grids
    -0.08
    POSITIVE LOGITS
    arian
    0.08
     suppose
    0.08
     seznam
    0.08
     subset
    0.07
    ([],
    0.07
    }->{
    0.07
     Agenda
    0.07
     collect
    0.07
     present
    0.07
    sem
    0.07
    Activations Density 0.021%

    No Known Activations