© 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. 94935
    Prev
    Next
    INDEX
    Explanations

    instead

    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
    žení
    -0.08
     ков
    -0.07
     kadar
    -0.07
     changing
    -0.07
     viss
    -0.07
    je
    -0.07
    áci
    -0.07
    (cur
    -0.07
     kada
    -0.07
    چې
    -0.07
    POSITIVE LOGITS
     Fest
    0.08
    dessen
    0.08
     наоборот
    0.08
     всего
    0.08
    исп
    0.08
    λη
    0.08
    �
    0.08
    0.07
    grunn
    0.07
     ine
    0.07
    Activations Density 0.034%
    No Known Activations