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. 30706
    Prev
    Next
    INDEX
    Explanations

    Sur

    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
     depends
    -0.08
    -ant
    -0.08
    (stderr
    -0.07
     ref
    -0.07
    SEE
    -0.07
    -energy
    -0.07
     histories
    -0.07
     anti
    -0.07
     signaling
    -0.07
     conserved
    -0.07
    POSITIVE LOGITS
     niece
    0.09
     ولد
    0.09
     colourful
    0.08
     iscr
    0.08
    一样
    0.08
     цвет
    0.08
     थी
    0.08
    /theme
    0.08
     répon
    0.08
     lanc
    0.08
    Activations Density 0.001%

    No Known Activations