© 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. 78330
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     Folge
    -0.07
     skoro
    -0.07
     Intersection
    -0.07
    .car
    -0.07
    kre
    -0.07
     My
    -0.07
     Same
    -0.06
     Cadillac
    -0.06
     Kosovo
    -0.06
     Kecamatan
    -0.06
    POSITIVE LOGITS
     যায়
    0.08
    Пер
    0.08
     Roo
    0.08
     даз
    0.08
     ಹೋಗ
    0.08
     Пер
    0.08
     psychiat
    0.08
    /schema
    0.08
    /ec
    0.08
     তিনি
    0.07
    Activations Density 0.002%

    No Known Activations