© 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. 68157
    Prev
    Next
    INDEX
    Explanations

    use

    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
     bleeding
    -0.08
    gles
    -0.08
    bled
    -0.07
     pulver
    -0.07
     vertical
    -0.07
     əlavə
    -0.07
    kr
    -0.07
    opedia
    -0.07
    iffel
    -0.07
     añadir
    -0.07
    POSITIVE LOGITS
    Specify
    0.08
     restante
    0.08
     destin
    0.08
    完整版
    0.08
     �
    0.07
     Gesamt
    0.07
    /control
    0.07
     komplette
    0.07
    textbox
    0.07
     gm
    0.07
    Activations Density 0.021%

    No Known Activations