© 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. 26180
    Prev
    Next
    INDEX
    Explanations

    Business, Technology, Diplomacy

    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
    Launcher
    -0.07
     repercussions
    -0.07
     Mil
    -0.07
    ிருக்க
    -0.07
     hol
    -0.07
    conce
    -0.07
    Nice
    -0.07
     lan
    -0.07
     migrations
    -0.07
     sitten
    -0.07
    POSITIVE LOGITS
     preparo
    0.08
    'él
    0.07
    ikation
    0.07
    വ്
    0.07
    asure
    0.07
     Sergeant
    0.07
     elaborar
    0.07
     النف
    0.07
     Kingston
    0.07
    гил
    0.07
    Activations Density 0.610%

    No Known Activations