© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68679
    Prev
    Next
    INDEX
    Explanations

    lightning

    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
    இ
    -0.10
     borderline
    -0.09
    mir
    -0.09
    亚
    -0.08
     darling
    -0.08
     aro
    -0.07
    fuura
    -0.07
    hum
    -0.07
    orderby
    -0.07
     jig
    -0.07
    POSITIVE LOGITS
     Physicians
    0.09
    速
    0.08
     chef
    0.08
     Computes
    0.07
    속
    0.07
    fully
    0.07
     Deals
    0.07
    般
    0.07
    击
    0.07
     burst
    0.07
    Activations Density 0.004%

    No Known Activations