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. 15-RESID-POST-AA
    6. 19289
    Prev
    Next
    INDEX
    Explanations

    exit/quit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NFT
    -0.08
    holt
    -0.08
     anteced
    -0.07
    经验
    -0.07
     zkušen
    -0.07
    huur
    -0.07
     tradicion
    -0.07
     histó
    -0.07
     경험
    -0.07
     sizing
    -0.07
    POSITIVE LOGITS
    (EXIT
    0.16
    退出
    0.15
    .exit
    0.15
    (exit
    0.14
    .Exit
    0.14
     shutting
    0.14
    	exit
    0.13
    _exit
    0.13
     gracefully
    0.13
    .EXIT
    0.13
    Activations Density 0.009%

    No Known Activations