© 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. 78463
    Prev
    Next
    INDEX
    Explanations

    Promises or future actions

    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
     cope
    -0.08
     kinda
    -0.08
     problemática
    -0.08
     нормы
    -0.07
    -0.07
     UUID
    -0.07
     whatever
    -0.07
     tension
    -0.07
     đối
    -0.07
    Underlying
    -0.07
    POSITIVE LOGITS
     Alm
    0.08
     તમને
    0.08
     contigo
    0.08
     tərəfindən
    0.08
     ayudarte
    0.08
    �
    0.08
     qualitative
    0.08
     Stich
    0.07
     proficiency
    0.07
     Dos
    0.07
    Activations Density 0.016%
    No Known Activations