© 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. 79326
    Prev
    Next
    INDEX
    Explanations

    astral projection and out-of-body

    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
     in
    -0.09
    `
    -0.08
    k
    -0.08
    ;
    -0.08
     على
    -0.08
     отк
    -0.08
     brewing
    -0.07
     hypertension
    -0.07
     km
    -0.07
     français
    -0.07
    POSITIVE LOGITS
     निकल
    0.09
     transmitted
    0.09
     außerhalb
    0.09
     relocated
    0.08
     Somehow
    0.08
    HOL
    0.08
     CENT
    0.08
     avent
    0.08
    .Direction
    0.08
     proyect
    0.08
    Activations Density 0.017%

    No Known Activations