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. 12899
    Prev
    Next
    INDEX
    Explanations

    8

    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
     verdi
    -0.09
     approximately
    -0.08
    ifornia
    -0.08
     Approximately
    -0.07
    /job
    -0.07
    imiz
    -0.07
    itura
    -0.07
    rán
    -0.07
    lık
    -0.07
    Kurz
    -0.07
    POSITIVE LOGITS
     flap
    0.09
     Yam
    0.08
    馆
    0.08
    儿
    0.07
     gastric
    0.07
     Spi
    0.07
    0.07
     EBIT
    0.07
     spi
    0.07
     esprit
    0.07
    Activations Density 0.027%

    No Known Activations