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. 76532
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
     aanwezig
    -0.10
     balconies
    -0.09
     ziyaret
    -0.09
     rooftop
    -0.09
     obisk
    -0.09
     penetration
    -0.09
     conqu
    -0.08
     održ
    -0.08
     Parque
    -0.08
     استان
    -0.08
    POSITIVE LOGITS
     calculators
    0.10
    谜
    0.10
     solving
    0.10
     equation
    0.09
    _inverse
    0.09
     mystery
    0.09
     Reverse
    0.09
    Solve
    0.09
     значение
    0.09
     reverse
    0.09
    Activations Density 0.115%

    No Known Activations