Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 419
    Prev
    Next
    INDEX
    Explanations

    code

    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
     closures
    -0.08
    伙伴
    -0.07
    ictured
    -0.07
     väh
    -0.07
     ಜೀವ
    -0.07
     sko
    -0.07
     đóng
    -0.07
    ,她
    -0.07
     Passion
    -0.07
     Riv
    -0.07
    POSITIVE LOGITS
    ::~
    0.09
     obten
    0.08
     extrusion
    0.08
     someday
    0.08
     JNICALL
    0.08
     extrap
    0.08
     мур
    0.08
     get
    0.08
     dada
    0.08
    	get
    0.08
    Activations Density 0.007%

    No Known Activations