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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 44101
    Prev
    Next
    INDEX
    Explanations

    Software configuration

    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
     fighting
    -0.09
    _attack
    -0.09
    Attack
    -0.09
     branching
    -0.09
     бор
    -0.09
     Attack
    -0.08
     claws
    -0.08
    感染
    -0.08
     همراه
    -0.08
     tận
    -0.08
    POSITIVE LOGITS
     directives
    0.09
     설정
    0.09
    .properties
    0.09
    .config
    0.09
    properties
    0.08
    LANG
    0.08
    键
    0.08
    字段
    0.08
    (setq
    0.08
    .USER
    0.08
    Activations Density 0.012%

    No Known Activations