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. 42154
    Prev
    Next
    INDEX
    Explanations

    wait

    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
    irteen
    -0.07
     amounted
    -0.07
    ousands
    -0.07
    进入
    -0.07
    ப்பட்டுள்ளது
    -0.07
     glow
    -0.07
     saturation
    -0.07
     заканч
    -0.07
    641
    -0.07
     жизнь
    -0.07
    POSITIVE LOGITS
     हिन्द
    0.08
     संद
    0.08
    unis
    0.08
     bzw
    0.08
     मैथ
    0.08
     नेपाली
    0.08
     गुजरात
    0.08
     त्र
    0.08
     parms
    0.08
     भारतीय
    0.07
    Activations Density 0.101%

    No Known Activations