© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    Personal feelings and reflection

    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
    _sender
    -0.08
    shalling
    -0.08
    .Uri
    -0.08
    -0.08
    uam
    -0.08
    raat
    -0.08
     handy
    -0.08
    props
    -0.08
    .Bind
    -0.07
     spooky
    -0.07
    POSITIVE LOGITS
     incess
    0.11
     relentlessly
    0.10
     relentless
    0.10
     selfish
    0.10
     obsessed
    0.10
     desperately
    0.09
     obsessive
    0.09
     addicted
    0.09
     endlessly
    0.08
     obsess
    0.08
    Activations Density 0.058%
    No Known Activations