© 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. 78148
    Prev
    Next
    INDEX
    Explanations

    weighted

    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
     viruses
    -0.08
     og
    -0.08
     eel
    -0.08
     double
    -0.08
     breast
    -0.08
     еж
    -0.07
     вирус
    -0.07
     chimp
    -0.07
     virus
    -0.07
     окру
    -0.07
    POSITIVE LOGITS
     weighting
    0.12
     weighing
    0.11
     weigh
    0.11
    .weight
    0.11
     weighed
    0.10
     Weighted
    0.10
     भार
    0.10
     weighted
    0.10
     وزن
    0.09
    weighted
    0.09
    Activations Density 0.005%

    No Known Activations