© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    average

    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
     Ganz
    -0.09
     choc
    -0.08
     veggie
    -0.08
     Gand
    -0.08
     dick
    -0.08
     Nakam
    -0.08
    etam
    -0.08
     Commonwealth
    -0.08
     flap
    -0.08
     davam
    -0.08
    POSITIVE LOGITS
     glimps
    0.08
    temps
    0.08
    іра
    0.08
     condolences
    0.08
     گذ
    0.08
     prejud
    0.08
     imperfections
    0.07
    ಗೊಂಡ
    0.07
     marginalized
    0.07
     إمكانية
    0.07
    Activations Density 0.015%

    No Known Activations