© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54392
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     imprimir
    -0.09
     वात
    -0.08
    riters
    -0.07
    inqu
    -0.07
    CRUD
    -0.07
    argar
    -0.07
    Pit
    -0.07
     acompanhado
    -0.07
     ofrecer
    -0.07
     cen
    -0.07
    POSITIVE LOGITS
    每天
    0.09
     instantaneous
    0.08
     actuelle
    0.08
     actuel
    0.08
    目前
    0.08
     தற்போது
    0.08
    每日
    0.08
     antwoorden
    0.08
    总
    0.08
    当前
    0.08
    Activations Density 0.025%

    No Known Activations