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. 42147
    Prev
    Next
    INDEX
    Explanations

    gibberish input

    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
     ಪೂ
    -0.08
     இண
    -0.08
     uitstek
    -0.07
     handcrafted
    -0.07
     llena
    -0.07
     century
    -0.07
     decad
    -0.07
    Estimated
    -0.07
     Damien
    -0.07
     II
    -0.07
    POSITIVE LOGITS
    asdf
    0.11
    Uw
    0.09
    乱码
    0.09
     Undefined
    0.09
     meaningless
    0.09
    哈哈
    0.09
    onsense
    0.09
     dummy
    0.09
    bla
    0.08
     absur
    0.08
    Activations Density 0.021%

    No Known Activations