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

    Neuronpedia

    APICircuit 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. 106292
    Prev
    Next
    INDEX
    Explanations

    16

    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
    ервые
    -0.09
     берен
    -0.09
     حافظ
    -0.09
     intervención
    -0.08
     inger
    -0.08
     Immer
    -0.08
    ಿತರ
    -0.08
     वृद्ध
    -0.08
    جهه
    -0.08
    awulo
    -0.08
    POSITIVE LOGITS
     product
    0.08
     thankfully
    0.07
    `.↵↵
    0.07
     tuple
    0.07
     splice
    0.07
     profesion
    0.07
     chakra
    0.07
    sí
    0.07
     repeats
    0.07
     resume
    0.07
    Activations Density 0.004%

    No Known Activations