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. 425
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     dad
    -0.09
    dad
    -0.09
     ফলে
    -0.08
     netto
    -0.07
    Dad
    -0.07
     Heritage
    -0.07
     sobe
    -0.07
     verhe
    -0.07
     Sout
    -0.07
     associate
    -0.07
    POSITIVE LOGITS
     વગેરે
    0.10
     എന്നീ
    0.10
     ஆகிய
    0.10
     그리고
    0.10
     എന്നിവ
    0.09
     וכו
    0.09
    ,以及
    0.08
    以及
    0.08
     आदि
    0.08
    そして
    0.08
    Activations Density 0.092%

    No Known Activations