© 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. 95079
    Prev
    Next
    INDEX
    Explanations

    class

    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
     të
    -0.08
    .AP
    -0.08
     ה
    -0.07
     територ
    -0.07
     třeba
    -0.07
     επιλογ
    -0.07
     lịch
    -0.07
    Divers
    -0.07
     graft
    -0.07
     пи
    -0.07
    POSITIVE LOGITS
    simp
    0.09
    iful
    0.08
    modern
    0.08
    members
    0.08
    outlined
    0.08
     saanud
    0.08
     equitable
    0.08
     facilité
    0.08
    alde
    0.08
    treated
    0.08
    Activations Density 0.001%

    No Known Activations