© 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. 44496
    Prev
    Next
    INDEX
    Explanations

    Alchemy

    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
    اط
    -0.08
     nag
    -0.08
    nag
    -0.07
     abb
    -0.07
     mins
    -0.07
     cognitive
    -0.07
     οι
    -0.07
     teg
    -0.07
     →
    -0.07
     Isabelle
    -0.07
    POSITIVE LOGITS
    ಂಧ
    0.08
     hospitalized
    0.08
    陪
    0.08
     gasolina
    0.08
     ಕ
    0.07
     سيارة
    0.07
    Lugar
    0.07
    ('/',
    0.07
     Мен
    0.07
     miest
    0.07
    Activations Density 0.005%

    No Known Activations