© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 13263
    Prev
    Next
    INDEX
    Explanations

    Order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fueled
    -0.08
     rellen
    -0.08
     pove
    -0.08
     காண
    -0.08
    Нап
    -0.07
     charged
    -0.07
     pob
    -0.07
     filles
    -0.07
     ind
    -0.07
     negatives
    -0.07
    POSITIVE LOGITS
    って
    0.08
     Standing
    0.08
     Gaz
    0.08
     ظل
    0.08
     transformation
    0.08
     standing
    0.07
     Krebs
    0.07
    0.07
    stahl
    0.07
    "D
    0.07
    Activations Density 0.001%

    No Known Activations