© 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. 29163
    Prev
    Next
    INDEX
    Explanations

    internal communication

    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
     illegally
    -0.08
    ARGV
    -0.08
    erweise
    -0.08
     extern
    -0.08
    Exterior
    -0.08
     Sule
    -0.08
     exterior
    -0.08
     genus
    -0.08
     elsif
    -0.08
     äußer
    -0.07
    POSITIVE LOGITS
     participation
    0.11
     rollout
    0.10
    薪
    0.10
     incentives
    0.10
     SMEs
    0.10
     Participation
    0.10
    particip
    0.10
    Participation
    0.09
     initiatives
    0.09
    Talent
    0.09
    Activations Density 0.029%

    No Known Activations