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. 131028
    Prev
    Next
    INDEX
    Explanations

    Р/р

    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
    ane
    -0.08
     अमेरिका
    -0.07
     त्या
    -0.07
     épr
    -0.07
    .Initial
    -0.07
    ্তা
    -0.07
    ədə
    -0.07
     inom
    -0.07
     नजर
    -0.07
    ,更
    -0.07
    POSITIVE LOGITS
    име
    0.08
     Detective
    0.08
    asons
    0.08
    Déc
    0.08
    komt
    0.07
    еспубли
    0.07
    cré
    0.07
    ingu
    0.07
     cushioning
    0.07
    Dict
    0.07
    Activations Density 0.001%

    No Known Activations