© 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. 3-RESID-POST-AA
    11. 13239
    Prev
    Next
    INDEX
    Explanations

    Qué

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SAL
    -0.09
     முட
    -0.07
     tilgjeng
    -0.07
     communal
    -0.07
    輸
    -0.07
     Tro
    -0.07
     induction
    -0.07
     முடிய
    -0.07
    uthu
    -0.07
     indicar
    -0.07
    POSITIVE LOGITS
    idium
    0.07
     stolen
    0.07
     verse
    0.07
     renovate
    0.07
     Bento
    0.07
    Coun
    0.07
     цел
    0.07
     counterfeit
    0.07
    Verse
    0.07
    موعة
    0.07
    Activations Density 0.007%

    No Known Activations