© 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. 44848
    Prev
    Next
    INDEX
    Explanations

    pronouns and personal interactions

    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
    _FLASH
    -0.08
     счастлив
    -0.08
     nationally
    -0.08
    425
    -0.08
     сказал
    -0.07
    Uploads
    -0.07
    893
    -0.07
     норм
    -0.07
     મત
    -0.07
    493
    -0.07
    POSITIVE LOGITS
    kezt
    0.09
    cups
    0.08
     Caps
    0.08
    ，以
    0.08
    wes
    0.08
     Schmerzen
    0.08
     sty
    0.08
     arches
    0.08
    iau
    0.07
    יקום
    0.07
    Activations Density 0.001%

    No Known Activations