© 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. 3-RESID-POST-AA
    11. 1388
    Prev
    Next
    INDEX
    Explanations

    Code/Foreign Language

    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
     ಗಳ
    -0.09
    Ascii
    -0.08
     Earn
    -0.08
     Gain
    -0.08
     oby
    -0.08
    Earn
    -0.07
     famosas
    -0.07
     impover
    -0.07
     Gains
    -0.07
     Và
    -0.07
    POSITIVE LOGITS
     distribu
    0.10
     distribuir
    0.09
     distrib
    0.08
     Distrib
    0.08
    Distrib
    0.08
     дисп
    0.08
     распредел
    0.08
     NZ
    0.07
     реклам
    0.07
     Zel
    0.07
    Activations Density 0.001%

    No Known Activations