© 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. 25283
    Prev
    Next
    INDEX
    Explanations

    virtual reality, neural interfaces

    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
    Castle
    -0.09
     castle
    -0.08
    -owned
    -0.07
     castles
    -0.07
     castell
    -0.07
    cta
    -0.07
    Orb
    -0.07
    usy
    -0.07
     behouden
    -0.07
    uksen
    -0.07
    POSITIVE LOGITS
     implants
    0.11
     implant
    0.11
    implant
    0.11
     nerves
    0.10
     hippoc
    0.10
     wired
    0.10
     injection
    0.10
     Implant
    0.10
     Gehir
    0.10
     wiring
    0.10
    Activations Density 0.018%

    No Known Activations