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. 90132
    Prev
    Next
    INDEX
    Explanations

    @ and square brackets

    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
     الدعم
    -0.07
     бой
    -0.07
    325
    -0.07
    tong
    -0.07
     soften
    -0.07
     pay
    -0.07
     settle
    -0.07
     प्रशिक्षण
    -0.07
     motor
    -0.06
     dissent
    -0.06
    POSITIVE LOGITS
    าณ
    0.08
    americana
    0.08
    ็ก
    0.08
    ежде
    0.08
     Creature
    0.08
    inya
    0.08
     Adresse
    0.08
     adorned
    0.08
     Petit
    0.08
    илак
    0.08
    Activations Density 0.001%

    No Known Activations