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. 56115
    Prev
    Next
    INDEX
    Explanations

    rnd

    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
     cumul
    -0.09
     Jasmine
    -0.09
     sanctioned
    -0.08
     scented
    -0.08
    ارة
    -0.08
    ดู
    -0.08
     resets
    -0.08
     لكن
    -0.08
    ppy
    -0.08
     cardiovascular
    -0.07
    POSITIVE LOGITS
    enery
    0.07
    ANC
    0.07
    uel
    0.07
     organización
    0.07
     Renew
    0.07
      		
    0.07
     tiy
    0.07
    uels
    0.07
    achel
    0.07
    ണ്ഡ
    0.07
    Activations Density 0.000%

    No Known Activations