© 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. 25174
    Prev
    Next
    INDEX
    Explanations

    admin

    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
     należy
    -0.08
     overarching
    -0.07
    may
    -0.07
    di
    -0.07
     objective
    -0.07
    negative
    -0.07
    within
    -0.07
     multiplier
    -0.07
    ovski
    -0.07
     lies
    -0.07
    POSITIVE LOGITS
     firestore
    0.09
     Garmin
    0.08
     бот
    0.08
     登
    0.08
    .observe
    0.08
    .device
    0.08
     '"'
    0.08
    .person
    0.08
     宣
    0.08
    览
    0.07
    Activations Density 0.001%

    No Known Activations