© 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. 44424
    Prev
    Next
    INDEX
    Explanations

    one or two

    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
     spheres
    -0.08
     zahlen
    -0.08
    ਦਾ
    -0.07
     verstehen
    -0.07
     duten
    -0.07
     multi
    -0.07
    ಕ್ಟ
    -0.07
     ausgest
    -0.07
     følgende
    -0.07
    ład
    -0.07
    POSITIVE LOGITS
     വീണ്ടും
    0.14
     ಮತ್ತೆ
    0.12
    再次
    0.12
     ફરી
    0.12
     tekrar
    0.12
     repetir
    0.11
    重复
    0.10
     wieder
    0.10
     erneut
    0.10
     снова
    0.10
    Activations Density 0.079%

    No Known Activations