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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95519
    Prev
    Next
    INDEX
    Explanations

    light and color

    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
     oversee
    -0.10
     overseeing
    -0.09
     rollback
    -0.09
     burocr
    -0.08
    纪律
    -0.08
     administrativas
    -0.08
    半年
    -0.08
    Rollback
    -0.08
     bureaucr
    -0.08
    Kot
    -0.08
    POSITIVE LOGITS
     photons
    0.14
     illumination
    0.13
     स्रोत
    0.11
     intensity
    0.11
     lighting
    0.11
     emitted
    0.11
     irradi
    0.11
    brightness
    0.11
     intensidad
    0.11
     iluminación
    0.11
    Activations Density 0.014%

    No Known Activations