© 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 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. 43538
    Prev
    Next
    INDEX
    Explanations

    bits, registers, programming

    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
    数学
    -0.08
    ensis
    -0.08
     specimens
    -0.07
     rival
    -0.07
    ēt
    -0.07
    批
    -0.07
     Chalk
    -0.07
     sequel
    -0.07
     criticism
    -0.07
    اش
    -0.07
    POSITIVE LOGITS
     bits
    0.12
     flags
    0.11
     Bits
    0.11
     बिट
    0.10
    flags
    0.10
     Flags
    0.10
    .bits
    0.10
    Bits
    0.10
    (bits
    0.09
    .flags
    0.09
    Activations Density 0.005%

    No Known Activations