© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 675
    Prev
    Next
    INDEX
    Explanations

    analog

    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
    447
    -0.08
    _nr
    -0.08
    ساعد
    -0.08
     변경
    -0.08
     nr
    -0.08
     usable
    -0.08
     vende
    -0.07
     کاربرد
    -0.07
    _si
    -0.07
    606
    -0.07
    POSITIVE LOGITS
     notoriously
    0.09
    -inspired
    0.08
     hype
    0.08
     classics
    0.08
     recorder
    0.08
     الأداء
    0.08
    Accumulator
    0.07
     notorious
    0.07
     mistakes
    0.07
     হার
    0.07
    Activations Density 0.005%

    No Known Activations