© 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. 78321
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    pick
    -0.09
     Semana
    -0.08
     japones
    -0.08
     seguito
    -0.07
    -layer
    -0.07
     hochwertigen
    -0.07
    hmen
    -0.07
    LONG
    -0.07
    but
    -0.07
     उम
    -0.07
    POSITIVE LOGITS
    ஆ
    0.09
     Administrative
    0.08
     Vì
    0.08
     =)
    0.07
     vài
    0.07
     ])
    0.07
     зав
    0.07
     //↵//
    0.07
    ुद
    0.07
     необходимости
    0.07
    Activations Density 0.155%

    No Known Activations