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. 65734
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
     unanim
    -0.08
    ná
    -0.07
     sú
    -0.07
    واز
    -0.07
     Kü
    -0.07
     uitgang
    -0.07
     مقد
    -0.07
     minister
    -0.07
    anzo
    -0.07
    -inc
    -0.07
    POSITIVE LOGITS
     год
    0.09
    /month
    0.08
    /day
    0.08
     সালের
    0.08
    /week
    0.08
     tím
    0.08
     heti
    0.08
    দিন
    0.08
     gar
    0.08
     precis
    0.07
    Activations Density 0.006%

    No Known Activations