© 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. 111031
    Prev
    Next
    INDEX
    Explanations

    Magnetic resonance imaging

    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
     wholesome
    -0.09
     주요
    -0.08
    (validation
    -0.08
     setbacks
    -0.08
     Mediterranean
    -0.08
    一道
    -0.08
    ्टर
    -0.08
    (ep
    -0.08
    алі
    -0.08
     бізнес
    -0.08
    POSITIVE LOGITS
     nuclei
    0.10
     spins
    0.10
     MHz
    0.09
     Gibbs
    0.09
     molecules
    0.09
     FFT
    0.09
     Hz
    0.08
    MHz
    0.08
     probes
    0.08
     (^
    0.08
    Activations Density 0.004%

    No Known Activations