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. 44124
    Prev
    Next
    INDEX
    Explanations

    pencil

    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
    æ
    -0.09
    ;.
    -0.08
    ,该
    -0.08
    .US
    -0.08
     caf
    -0.08
    «.
    -0.08
     cef
    -0.08
     Compiler
    -0.08
     미국
    -0.08
     खाते
    -0.07
    POSITIVE LOGITS
    陰
    0.08
     lace
    0.08
     obsessed
    0.08
     thinks
    0.08
     Holden
    0.08
    (el
    0.08
     lightly
    0.07
    0.07
    	wire
    0.07
     willow
    0.07
    Activations Density 0.006%

    No Known Activations