© 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. 45746
    Prev
    Next
    INDEX
    Explanations

    Self compassion/emotional regulation

    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
     측
    -0.09
     quelcon
    -0.08
    ומות
    -0.08
     공간
    -0.08
     그의
    -0.08
     반복
    -0.08
    Sesion
    -0.08
    აციის
    -0.08
    игура
    -0.08
    (Big
    -0.08
    POSITIVE LOGITS
    score
    0.07
    vada
    0.07
    mot
    0.07
    ых
    0.07
    rd
    0.07
    locked
    0.07
    LD
    0.07
     tribute
    0.07
    rey
    0.07
    хара
    0.07
    Activations Density 0.005%

    No Known Activations