© 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. 91500
    Prev
    Next
    INDEX
    Explanations

    vent

    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
     coat
    -0.09
     내부
    -0.08
     מא
    -0.08
     palettes
    -0.07
     slid
    -0.07
     Illumin
    -0.07
    isha
    -0.07
     menus
    -0.07
     God's
    -0.07
     Gardens
    -0.07
    POSITIVE LOGITS
     ultraviolet
    0.10
     UV
    0.10
     dada
    0.09
    UV
    0.08
     securities
    0.08
    _RATE
    0.08
    缴
    0.08
     statutory
    0.08
     estím
    0.07
    ేస్త
    0.07
    Activations Density 0.003%

    No Known Activations