© 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. 95256
    Prev
    Next
    INDEX
    Explanations

    magic tricks

    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
     aanb
    -0.10
     inland
    -0.09
     тос
    -0.09
     finner
    -0.08
     hourly
    -0.08
     socioeconomic
    -0.08
     gior
    -0.08
     климат
    -0.08
    urban
    -0.08
     المدن
    -0.08
    POSITIVE LOGITS
     magician
    0.13
     mesmerizing
    0.11
     deceptive
    0.10
    magic
    0.10
     mystery
    0.10
    _magic
    0.10
     illusions
    0.10
     deception
    0.10
     illusion
    0.10
     mesmer
    0.10
    Activations Density 0.024%

    No Known Activations