© 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. 54331
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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
     musicals
    -0.09
     വൈറ
    -0.09
     viral
    -0.08
     soot
    -0.08
     SOUND
    -0.08
    silver
    -0.08
     AUDIO
    -0.08
    criptors
    -0.08
     darkness
    -0.08
    ussing
    -0.08
    POSITIVE LOGITS
    -integr
    0.09
    .email
    0.08
    Integr
    0.08
    旧
    0.08
    .integr
    0.08
    .[
    0.08
    ם
    0.08
    .public
    0.08
    .integration
    0.07
    Unlock
    0.07
    Activations Density 0.003%

    No Known Activations