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. 41972
    Prev
    Next
    INDEX
    Explanations

    daemon

    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
    வ்வ
    -0.08
     distant
    -0.07
    ையும்
    -0.07
    ("-
    -0.07
    ம்ப
    -0.07
     ingez
    -0.07
     விட
    -0.07
    வு
    -0.07
    .thumb
    -0.07
    ერ
    -0.07
    POSITIVE LOGITS
     కంప
    0.09
     ഹെ
    0.09
     FI
    0.08
     कम्प
    0.08
     työn
    0.08
     pyt
    0.07
     രാത്ര
    0.07
     Beno
    0.07
     práce
    0.07
     Flo
    0.07
    Activations Density 0.000%

    No Known Activations