© 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. 3-RESID-POST-AA
    11. 2804
    Prev
    Next
    INDEX
    Explanations

    滤

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concerne
    -0.08
     Kont
    -0.07
     darah
    -0.07
     Mater
    -0.07
     Fut
    -0.07
     sweating
    -0.07
     fec
    -0.07
    eneric
    -0.07
     gest
    -0.07
     Foot
    -0.07
    POSITIVE LOGITS
     ike
    0.08
     Ike
    0.08
     conductor
    0.08
    ри
    0.08
     homogeneous
    0.07
    ρία
    0.07
     пай
    0.07
    ▒
    0.07
    chain
    0.07
     Mink
    0.07
    Activations Density 0.003%

    No Known Activations