© 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. 95394
    Prev
    Next
    INDEX
    Explanations

    Minimization/Maximization

    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
     equipped
    -0.07
     Olivier
    -0.07
     Oliver
    -0.07
     Middleton
    -0.07
     commonly
    -0.07
     divided
    -0.07
     together
    -0.07
     tattoo
    -0.07
    contr
    -0.07
     figur
    -0.07
    POSITIVE LOGITS
     jurídicas
    0.09
     naquela
    0.09
     rápidamente
    0.08
    usas
    0.08
    menities
    0.08
    泊
    0.07
     भू
    0.07
     behoort
    0.07
     daquela
    0.07
     þá
    0.07
    Activations Density 0.064%

    No Known Activations