© 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. 7-RESID-POST-AA
    11. 1160
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    Tea
    -0.09
     tea
    -0.08
     Tea
    -0.07
     markets
    -0.07
    人士
    -0.07
     wards
    -0.07
    旅行
    -0.07
     designers
    -0.07
    客服
    -0.07
     Toolkit
    -0.07
    POSITIVE LOGITS
    ément
    0.08
    aging
    0.08
    din
    0.08
    acją
    0.08
     થય
    0.08
     emoz
    0.08
    SHORT
    0.08
    solid
    0.07
    ermont
    0.07
    cement
    0.07
    Activations Density 0.000%

    No Known Activations