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. 60669
    Prev
    Next
    INDEX
    Explanations

    varied text snippets

    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
    。而
    -0.08
    。所以
    -0.08
    Ny
    -0.08
     yangu
    -0.08
     delinc
    -0.07
    Olymp
    -0.07
     બદ
    -0.07
     ::↵↵
    -0.07
    Rx
    -0.07
    。当然
    -0.07
    POSITIVE LOGITS
     खोल
    0.08
     brightly
    0.08
    -первых
    0.07
    ;↵
    0.07
    aman
    0.07
    ikh
    0.07
    displaystyle
    0.07
    .enums
    0.07
     nhiên
    0.07
    	q
    0.07
    Activations Density 0.375%

    No Known Activations