© 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. 79017
    Prev
    Next
    INDEX
    Explanations

    HTML labels and divs

    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
    cią
    -0.07
     krypt
    -0.07
    _User
    -0.07
    foundation
    -0.07
    Infinity
    -0.07
     extremely
    -0.07
    rypt
    -0.07
     σειρά
    -0.07
    עס
    -0.07
     Nickel
    -0.07
    POSITIVE LOGITS
     Maduro
    0.08
     chica
    0.08
     اش
    0.08
     blom
    0.08
     Ane
    0.08
     $('<
    0.07
     Perkins
    0.07
     apoptosis
    0.07
     protests
    0.07
     Parm
    0.07
    Activations Density 0.004%

    No Known Activations