Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43253
    Prev
    Next
    INDEX
    Explanations

    enter

    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
     dilution
    -0.07
    чер
    -0.07
    (","
    -0.07
    \Db
    -0.07
    шается
    -0.07
    сул
    -0.07
     Contents
    -0.07
     princípio
    -0.07
    hlen
    -0.07
     дорого
    -0.07
    POSITIVE LOGITS
    整数
    0.09
    integer
    0.09
    .Integer
    0.09
     gült
    0.08
    _integer
    0.08
     integer
    0.08
    Integer
    0.08
     integers
    0.08
    .Conv
    0.08
     obedient
    0.07
    Activations Density 0.004%

    No Known Activations