© 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. 79491
    Prev
    Next
    INDEX
    Explanations

    CNC machines

    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
    Competitive
    -0.08
     fats
    -0.08
     fec
    -0.07
     airing
    -0.07
     morale
    -0.07
    とは
    -0.07
     aired
    -0.07
    зал
    -0.07
     Junction
    -0.07
     distinctly
    -0.07
    POSITIVE LOGITS
     movements
    0.09
     scans
    0.09
    beweg
    0.09
     coordinates
    0.09
    -speed
    0.09
    Coordinates
    0.09
     Cartesian
    0.08
     движения
    0.08
     Beweg
    0.08
     sweeping
    0.08
    Activations Density 0.011%

    No Known Activations