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. 77552
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
     revel
    -0.09
     Yam
    -0.08
    impi
    -0.08
     Awak
    -0.08
     Delf
    -0.08
     dilig
    -0.08
     fidèle
    -0.08
     وَ
    -0.08
     전체
    -0.08
    ebol
    -0.07
    POSITIVE LOGITS
    0.08
    webkit
    0.08
    "},
    0.08
    amt
    0.07
     claws
    0.07
    +-+-+-+-+-+-+-+-
    0.07
    annya
    0.07
    आ
    0.07
     Carr
    0.07
    ाँच
    0.07
    Activations Density 0.031%

    No Known Activations