© 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. 605
    Prev
    Next
    INDEX
    Explanations

    covers

    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
     קשר
    -0.08
     asbestos
    -0.08
     ба
    -0.07
     هزینه
    -0.07
    �
    -0.07
    石
    -0.07
     ఆధ
    -0.07
     دنبال
    -0.07
     ವಿವ
    -0.07
    AKA
    -0.07
    POSITIVE LOGITS
     akt
    0.08
    പ്പെട്ട
    0.08
     encourage
    0.08
     prescribe
    0.08
    estrians
    0.08
     loosen
    0.08
    mani
    0.08
     makar
    0.08
    ittura
    0.07
     brace
    0.07
    Activations Density 0.001%

    No Known Activations