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. 60467
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    佳
    -0.08
     ير
    -0.08
    =args
    -0.07
    temps
    -0.07
     union
    -0.07
    apes
    -0.07
    lea
    -0.07
    ter
    -0.07
    lambda
    -0.07
    tec
    -0.07
    POSITIVE LOGITS
     Magistr
    0.09
     облег
    0.09
     aigu
    0.09
     wichtigste
    0.08
     citt
    0.08
    وعية
    0.08
     Astro
    0.08
     स्त
    0.08
     JVM
    0.08
     völl
    0.08
    Activations Density 0.002%

    No Known Activations