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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130805
    Prev
    Next
    INDEX
    Explanations

    kingdoms and empires

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rome
    -0.12
     Germania
    -0.10
     Germany
    -0.09
     Italy
    -0.09
     Nicholas
    -0.09
     Deutschland
    -0.09
     Arabia
    -0.09
     Russia
    -0.09
     göt
    -0.09
     Romania
    -0.09
    POSITIVE LOGITS
     centralized
    0.09
     puissant
    0.09
     s
    0.09
     powerful
    0.09
     Mar
    0.08
     feud
    0.08
     courts
    0.08
     resur
    0.08
     Param
    0.08
     силь
    0.08
    Activations Density 0.009%

    No Known Activations