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. 48434
    Prev
    Next
    INDEX
    Explanations

    WebRTC SDP

    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
    èn
    -0.09
     Colonel
    -0.08
     tuple
    -0.08
     Loyal
    -0.08
    Saint
    -0.08
     Saint
    -0.08
    /functions
    -0.08
     firef
    -0.08
     快乐
    -0.08
    /libs
    -0.07
    POSITIVE LOGITS
     románt
    0.09
     hyr
    0.08
     iniciar
    0.08
    随后
    0.08
     surg
    0.08
    OH
    0.08
    提交
    0.08
    启动
    0.08
    ulare
    0.08
     اولیه
    0.08
    Activations Density 0.001%

    No Known Activations