© 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. 95665
    Prev
    Next
    INDEX
    Explanations

    pistons and engines

    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
    全国
    -0.09
     BFS
    -0.08
    ldy
    -0.08
    .www
    -0.08
     trebalo
    -0.08
     Fourier
    -0.07
     eksport
    -0.07
     ets
    -0.07
     ed
    -0.07
    fik
    -0.07
    POSITIVE LOGITS
     piston
    0.11
    Cylinder
    0.10
     cylinders
    0.10
     Cylinder
    0.09
     cavities
    0.09
     chambers
    0.09
     Cartridge
    0.09
     насос
    0.09
     цилинд
    0.09
     Cups
    0.09
    Activations Density 0.009%

    No Known Activations