© 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. 3-RESID-POST-AA
    11. 2531
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chiefly
    -0.08
    678
    -0.08
     autobi
    -0.08
     بع
    -0.08
     �
    -0.08
     możliwości
    -0.08
     облад
    -0.07
    裏
    -0.07
     AGE
    -0.07
     느
    -0.07
    POSITIVE LOGITS
     cuadr
    0.08
    :R
    0.07
     Jaw
    0.07
     Jac
    0.07
    Jac
    0.07
     Fidelity
    0.07
     Extract
    0.07
    fabs
    0.07
     gcd
    0.07
     combine
    0.07
    Activations Density 0.091%

    No Known Activations