© 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. 3-RESID-POST-AA
    11. 13327
    Prev
    Next
    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfection
    -0.09
     accomplishment
    -0.09
     electrode
    -0.08
     legitimacy
    -0.08
    aves
    -0.08
     qualification
    -0.08
     electives
    -0.08
     proprietary
    -0.08
     Achievement
    -0.08
     electrodes
    -0.07
    POSITIVE LOGITS
    /grid
    0.09
    Sight
    0.08
    'ch
    0.08
    пен
    0.07
    (circle
    0.07
     minutos
    0.07
    _cent
    0.07
     분
    0.07
     случаи
    0.07
    あります
    0.07
    Activations Density 0.002%

    No Known Activations