© 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. 31185
    Prev
    Next
    INDEX
    Explanations

    original

    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
    เข้า
    -0.09
     promulg
    -0.09
     Regulations
    -0.08
    iggs
    -0.08
    mén
    -0.08
    หัว
    -0.08
     pitcher
    -0.08
    Basics
    -0.08
     نحو
    -0.08
    ("${
    -0.07
    POSITIVE LOGITS
     unchanged
    0.13
     intact
    0.12
     untouched
    0.12
     unaffected
    0.12
     originals
    0.10
     originale
    0.09
     original
    0.09
     apart
    0.09
     اصلی
    0.09
     asli
    0.09
    Activations Density 0.010%

    No Known Activations