© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24634
    Prev
    Next
    INDEX
    Explanations

    splitting strings

    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
     berger
    -0.08
     profesión
    -0.08
    य
    -0.08
    ती
    -0.07
    _prof
    -0.07
     Duk
    -0.07
    ्सा
    -0.07
    Profes
    -0.07
     Gab
    -0.07
     feste
    -0.07
    POSITIVE LOGITS
     ਹਰ
    0.08
     ہر
    0.08
    odz
    0.08
     للتح
    0.07
     eliminar
    0.07
     unabhängig
    0.07
     finanzi
    0.07
     EVERY
    0.07
     neutr
    0.07
     الاول
    0.07
    Activations Density 0.006%

    No Known Activations