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. 58553
    Prev
    Next
    INDEX
    Explanations

    bulk

    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
     Fab
    -0.08
    玄机
    -0.08
    .HTML
    -0.07
    617
    -0.07
     Prima
    -0.07
     时间
    -0.07
     brillo
    -0.07
     συμβ
    -0.07
     κάπο
    -0.07
     horoscope
    -0.07
    POSITIVE LOGITS
    Chunk
    0.08
     odpr
    0.08
     coloc
    0.08
     entry
    0.08
    forma
    0.08
     contiguous
    0.08
     ammonia
    0.08
     áit
    0.08
    .Mutable
    0.08
     ukusuka
    0.08
    Activations Density 0.007%

    No Known Activations