© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 68854
    Prev
    Next
    INDEX
    Explanations

    extract

    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
     意
    -0.09
    _Send
    -0.09
    	Send
    -0.09
    	send
    -0.08
     serius
    -0.08
     enviados
    -0.08
     वरिष्ठ
    -0.08
    រស
    -0.08
    践
    -0.08
     电话
    -0.08
    POSITIVE LOGITS
    _unpack
    0.13
    .unpack
    0.13
     unpack
    0.12
     unmar
    0.12
     extraction
    0.12
    .decode
    0.11
     decoded
    0.11
    Extract
    0.11
     extracting
    0.11
     parsing
    0.11
    Activations Density 0.011%

    No Known Activations