© 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. 25164
    Prev
    Next
    INDEX
    Explanations

    disco

    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
     रे
    -0.08
    typen
    -0.08
     arbitration
    -0.08
     suscept
    -0.08
     negoci
    -0.08
     Sir
    -0.08
    �
    -0.08
    Sir
    -0.07
     ली
    -0.07
     concess
    -0.07
    POSITIVE LOGITS
     ফির
    0.09
     Prot
    0.08
     cockpit
    0.08
     vintage
    0.08
     videot
    0.08
     millennium
    0.07
     legacy
    0.07
     একটা
    0.07
     кос
    0.07
    Death
    0.07
    Activations Density 0.003%

    No Known Activations