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. 15-RESID-POST-AA
    6. 19406
    Prev
    Next
    INDEX
    Explanations

    numbers with zero

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queste
    -0.08
    "',
    -0.08
    "'
    -0.08
    “These
    -0.07
     questi
    -0.07
    ",
    -0.07
    "',↵
    -0.07
    "`↵↵
    -0.07
     Tao
    -0.07
     }),↵↵
    -0.07
    POSITIVE LOGITS
    =↵
    0.09
    ёна
    0.09
     deren
    0.09
     მან
    0.09
    resultado
    0.09
    uiden
    0.08
    Resultado
    0.08
    unas
    0.08
     результат
    0.08
     ardından
    0.08
    Activations Density 0.011%

    No Known Activations