© 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. 75718
    Prev
    Next
    INDEX
    Explanations

    Physics constants

    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
    (place
    -0.08
    이터
    -0.08
     bloom
    -0.08
     VLAN
    -0.08
    Summary
    -0.08
    ่ว
    -0.08
     voltage
    -0.07
    Flowers
    -0.07
    Ung
    -0.07
    ynamic
    -0.07
    POSITIVE LOGITS
    constants
    0.11
     constants
    0.11
    /constants
    0.11
     Constants
    0.10
    (constants
    0.10
    Constants
    0.10
    是多少
    0.10
    _constants
    0.10
    ħ
    0.10
     ħ
    0.09
    Activations Density 0.003%

    No Known Activations