Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58783
    Prev
    Next
    INDEX
    Explanations

    assembly code

    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
     instagram
    -0.10
     volunteer
    -0.09
     Goodreads
    -0.09
     brides
    -0.09
    本科
    -0.09
    COVID
    -0.09
     weib
    -0.09
    聊天
    -0.09
    _chat
    -0.08
    投入
    -0.08
    POSITIVE LOGITS
    opcode
    0.13
    Opcode
    0.13
     opcode
    0.13
     Opcode
    0.12
     instruk
    0.12
     mnemonic
    0.11
     comandos
    0.11
    Insn
    0.11
     Instruction
    0.11
    Instruction
    0.11
    Activations Density 0.008%

    No Known Activations