© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 111520
    Prev
    Next
    INDEX
    Explanations

    large

    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
     pus
    -0.08
    yled
    -0.08
     Silverado
    -0.08
    בר
    -0.07
    TERN
    -0.07
     �
    -0.07
    анс
    -0.07
     Boc
    -0.07
     aur
    -0.07
    pendency
    -0.07
    POSITIVE LOGITS
     جدًا
    0.10
     enough
    0.08
     genug
    0.08
    -scale
    0.08
     جداً
    0.08
    ‌تر
    0.08
    ತನ
    0.08
    ITUDE
    0.07
    -quality
    0.07
    篇
    0.07
    Activations Density 0.041%

    No Known Activations