© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70145
    Prev
    Next
    INDEX
    Explanations

    gaming performance

    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
     urn
    -0.10
     amendment
    -0.10
     oplysninger
    -0.09
     confidentiality
    -0.08
     amend
    -0.08
     amendments
    -0.08
     Amend
    -0.08
     taboo
    -0.08
    dang
    -0.08
     urna
    -0.08
    POSITIVE LOGITS
     Ryzen
    0.13
     GPUs
    0.12
     GPU
    0.12
    GPU
    0.11
     fullscreen
    0.11
     Nvidia
    0.11
     shaders
    0.10
     NVIDIA
    0.10
    _CPU
    0.10
     ASUS
    0.10
    Activations Density 0.015%

    No Known Activations