© 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. 108472
    Prev
    Next
    INDEX
    Explanations

    Code/Instructions/AI

    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
     creepy
    -0.08
    _initial
    -0.07
    -lived
    -0.07
     car
    -0.07
    _dummy
    -0.07
     artificially
    -0.07
    SL
    -0.07
     dogs
    -0.07
    -labelled
    -0.07
     Phen
    -0.07
    POSITIVE LOGITS
    ✅
    0.08
     recomienda
    0.08
    ŋ
    0.08
     gabinete
    0.08
     incandescent
    0.08
    Pacific
    0.08
    �
    0.08
    ונט
    0.08
     deseja
    0.08
    tai
    0.08
    Activations Density 0.456%

    No Known Activations