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. 42109
    Prev
    Next
    INDEX
    Explanations

    open air

    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
     shorten
    -0.09
     shorter
    -0.08
     lashes
    -0.08
     swell
    -0.08
     Embedded
    -0.08
     interna
    -0.08
    infer
    -0.08
    ítás
    -0.07
     Sutton
    -0.07
    σύ
    -0.07
    POSITIVE LOGITS
    取消
    0.09
     sculptures
    0.08
     memorial
    0.08
    <{
    0.08
     monuments
    0.08
    解除
    0.07
     organisers
    0.07
     organizers
    0.07
     covering
    0.07
     statue
    0.07
    Activations Density 0.005%

    No Known Activations