© 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. 11-RESID-POST-AA
    11. 26332
    Prev
    Next
    INDEX
    Explanations

    templates, logs

    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
     looming
    -0.08
    apọ
    -0.08
     crisi
    -0.08
    oneg
    -0.08
     amea
    -0.08
     evil
    -0.08
    kẹ
    -0.07
     crises
    -0.07
     traditionally
    -0.07
     stubborn
    -0.07
    POSITIVE LOGITS
     జరిగిన
    0.12
     successfully
    0.12
     Successfully
    0.11
     జరిగింది
    0.11
    Successfully
    0.10
     நடைபெற்ற
    0.10
     tamin
    0.10
     നടന്ന
    0.10
     जिसने
    0.10
     Received
    0.10
    Activations Density 0.060%

    No Known Activations