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. 106286
    Prev
    Next
    INDEX
    Explanations

    code computation

    np_max-act · gemini-2.0-flash

    the beginning-of-text control marker (i.e., the special token that denotes the start of a document/segment).

    oai_token-act-pair · gpt-5Triggered by @tatsatx
    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
     estates
    -0.09
     भार
    -0.08
     बां
    -0.08
     setbacks
    -0.08
    手续
    -0.08
     estate
    -0.08
    -0.08
    estimate
    -0.08
     estimates
    -0.08
     जंगल
    -0.08
    POSITIVE LOGITS
    乱码
    0.11
     programmer
    0.10
     programmers
    0.10
     Compiler
    0.10
     foo
    0.10
     ожида
    0.10
    打印
    0.10
     programmation
    0.10
    第一次
    0.10
     executar
    0.09
    Activations Density 0.023%

    No Known Activations