© 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. 95171
    Prev
    Next
    INDEX
    Explanations

    educational text

    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
     syndicated
    -0.11
     underserved
    -0.09
    打造
    -0.09
     dành
    -0.09
     nationwide
    -0.08
     Airbnb
    -0.08
     anonym
    -0.08
     Nigerian
    -0.08
     emo
    -0.08
     racial
    -0.08
    POSITIVE LOGITS
     torque
    0.12
     magnitude
    0.12
     Hertz
    0.12
     الكهربائية
    0.12
     Jou
    0.12
     physic
    0.12
     semiconductor
    0.11
     geometr
    0.11
    _energy
    0.11
     mathem
    0.11
    Activations Density 0.050%

    No Known Activations