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. 97061
    Prev
    Next
    INDEX
    Explanations

    code and technical details

    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
     energetic
    -0.08
     country's
    -0.08
     шлях
    -0.07
     मिन
    -0.07
     ecology
    -0.07
     energet
    -0.07
    	min
    -0.07
     ऊर्जा
    -0.07
     Мин
    -0.07
     Ener
    -0.07
    POSITIVE LOGITS
     tete
    0.08
    Dev
    0.08
    ST
    0.08
     sauveg
    0.08
    Sau
    0.08
    .CONTENT
    0.07
    BCC
    0.07
    保存
    0.07
     materias
    0.07
    itaanka
    0.07
    Activations Density 0.000%

    No Known Activations