© 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. 7-RESID-POST-AA
    6. 848
    Prev
    Next
    INDEX
    Explanations

    synthetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sandwiches
    -0.07
    (open
    -0.07
    (stream
    -0.07
    お願い
    -0.07
    ies
    -0.07
    (trans
    -0.07
     मोबाइल
    -0.07
    맨
    -0.07
    gram
    -0.07
    есь
    -0.07
    POSITIVE LOGITS
     preservatives
    0.08
     zvin
    0.08
     Lon
    0.08
     qü
    0.08
    �
    0.08
     sindic
    0.08
     scents
    0.08
     Lidl
    0.08
     Oils
    0.08
     oda
    0.08
    Activations Density 0.004%

    No Known Activations