© 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. 23-RESID-POST-AA
    11. 47835
    Prev
    Next
    INDEX
    Explanations

    dis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itelisted
    -0.09
    ENSITIVE
    -0.09
    닫
    -0.09
     irritated
    -0.09
     qoy
    -0.09
     activating
    -0.08
     chiq
    -0.08
     positieve
    -0.08
    سبة
    -0.08
     chí
    -0.08
    POSITIVE LOGITS
    ruption
    0.15
    array
    0.15
    integration
    0.14
    arrays
    0.14
    location
    0.13
    organization
    0.13
    locations
    0.12
    union
    0.12
    alignment
    0.12
    service
    0.11
    Activations Density 0.015%

    No Known Activations