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. 42117
    Prev
    Next
    INDEX
    Explanations

    7

    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
     mors
    -0.07
    破
    -0.07
     intuitive
    -0.07
     తొ
    -0.07
    Scheduler
    -0.07
    -playing
    -0.07
     sway
    -0.07
    撞
    -0.07
    Chez
    -0.07
    ೂಲ
    -0.07
    POSITIVE LOGITS
     kategori
    0.09
    ynthesize
    0.09
     onu
    0.08
     textarea
    0.08
     onion
    0.08
     Kartoff
    0.08
    oweit
    0.08
     hashtags
    0.07
    łat
    0.07
     sobren
    0.07
    Activations Density 0.003%

    No Known Activations