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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110220
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     Cis
    -0.08
    ાશે
    -0.08
    ioon
    -0.07
    bond
    -0.07
    ड्ड
    -0.07
     handing
    -0.07
    -0.07
    .accounts
    -0.07
    .nodes
    -0.07
     drilled
    -0.07
    POSITIVE LOGITS
    анов
    0.09
     chiếc
    0.08
    �
    0.08
    ️
    0.08
     vivid
    0.08
     unmistak
    0.08
     bustling
    0.07
    وف
    0.07
     variations
    0.07
     genetically
    0.07
    Activations Density 0.006%
    No Known Activations