© 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. 69410
    Prev
    Next
    INDEX
    Explanations

    byte

    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
     analges
    -0.09
     oregano
    -0.08
     farmer
    -0.08
    婚
    -0.08
     matrimon
    -0.08
     magnific
    -0.08
     juices
    -0.08
     majest
    -0.08
    othy
    -0.08
     begon
    -0.07
    POSITIVE LOGITS
    Compiled
    0.10
    .instructions
    0.10
     compiled
    0.09
    Compilation
    0.09
    代码
    0.09
    compiled
    0.09
    Instruction
    0.08
    .code
    0.08
    Compiler
    0.08
    Insn
    0.08
    Activations Density 0.004%

    No Known Activations