© 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. 108804
    Prev
    Next
    INDEX
    Explanations

    management

    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
    NT
    -0.09
    nt
    -0.08
    NC
    -0.08
     speciality
    -0.08
     Revis
    -0.08
     NT
    -0.08
     lazer
    -0.07
    chtime
    -0.07
     Charm
    -0.07
    chsel
    -0.07
    POSITIVE LOGITS
    贯彻
    0.12
    体系
    0.12
     구축
    0.10
    贯
    0.10
     perme
    0.10
     rakent
    0.08
     instituted
    0.08
    落实
    0.08
    建设
    0.08
     gripping
    0.08
    Activations Density 0.012%

    No Known Activations