© 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. 129333
    Prev
    Next
    INDEX
    Explanations

    ent

    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
    中央
    -0.09
     Central
    -0.08
     primarily
    -0.08
     problemlos
    -0.08
     Bose
    -0.08
     voornamelijk
    -0.08
     específico
    -0.08
     centrally
    -0.08
     EVENT
    -0.08
     hervorragend
    -0.07
    POSITIVE LOGITS
     excavation
    0.08
     값
    0.08
     dons
    0.08
    ures
    0.08
    orship
    0.08
    력이
    0.07
     witches
    0.07
    치는
    0.07
    Value
    0.07
    icism
    0.07
    Activations Density 0.000%

    No Known Activations