© 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. 47387
    Prev
    Next
    INDEX
    Explanations

    honeymoon

    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
    cience
    -0.08
    গ
    -0.07
    mouse
    -0.07
    hta
    -0.07
    portivo
    -0.07
    μία
    -0.07
    -human
    -0.07
    Shift
    -0.07
    ğun
    -0.07
    Moh
    -0.07
    POSITIVE LOGITS
     honeymoon
    0.11
    ertura
    0.08
     periodo
    0.07
     этап
    0.07
    hone
    0.07
    estly
    0.07
    阶段
    0.07
     Geological
    0.07
     تون
    0.07
    Epoch
    0.07
    Activations Density 0.005%

    No Known Activations