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. 12408
    Prev
    Next
    INDEX
    Explanations

    boolean logic

    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
    集
    -0.09
    ieval
    -0.08
    ினர்
    -0.08
    avaient
    -0.08
    (Screen
    -0.08
    तात
    -0.07
    ిస్తున్నారు
    -0.07
    (ID
    -0.07
     discouraged
    -0.07
     aument
    -0.07
    POSITIVE LOGITS
     lhs
    0.09
    worthiness
    0.08
     rhs
    0.08
     sóc
    0.08
     同
    0.08
    നിക്ക്
    0.08
    lhs
    0.08
     ഞാൻ
    0.08
     Agree
    0.08
     ack
    0.07
    Activations Density 0.002%

    No Known Activations