© 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. 3-RESID-POST-AA
    11. 13273
    Prev
    Next
    INDEX
    Explanations

    doc

    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
    🏼
    -0.08
    赖
    -0.08
    óc
    -0.08
     rot
    -0.08
    ее
    -0.08
    �
    -0.08
     respite
    -0.07
    etus
    -0.07
     konkre
    -0.07
    设备
    -0.07
    POSITIVE LOGITS
     kinh
    0.08
     violent
    0.08
     Abel
    0.08
     получ
    0.08
     Lady
    0.07
     Guy
    0.07
     carreg
    0.07
     Kini
    0.07
     दुर्�
    0.07
    ijnen
    0.07
    Activations Density 0.006%

    No Known Activations