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. 76083
    Prev
    Next
    INDEX
    Explanations

    init

    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
    走势
    -0.08
    Downloading
    -0.08
     Vorm
    -0.08
    okestatic
    -0.08
     monitoring
    -0.08
    (Rem
    -0.08
     વગ
    -0.08
     actionable
    -0.08
    	Local
    -0.08
     visok
    -0.08
    POSITIVE LOGITS
    constructor
    0.15
     constructor
    0.13
     Constructor
    0.13
    _constructor
    0.12
     ctor
    0.12
    Constructor
    0.12
    	constructor
    0.11
     initializer
    0.11
    初始化
    0.11
    _init
    0.10
    Activations Density 0.009%

    No Known Activations