© 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. 113617
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     covid
    -0.09
     pandemia
    -0.09
    COVID
    -0.09
     موارد
    -0.08
     pandemic
    -0.08
     Renewable
    -0.08
    措
    -0.08
    -0.08
     umbrellas
    -0.08
    (plan
    -0.08
    POSITIVE LOGITS
     eax
    0.12
     DWORD
    0.12
    .asm
    0.12
    eax
    0.11
    DWORD
    0.11
     syscall
    0.11
     ELF
    0.10
    Opcode
    0.10
     LLVM
    0.10
    cdecl
    0.10
    Activations Density 0.011%
    No Known Activations