© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47451
    Prev
    Next
    INDEX
    Explanations

    Childbirth roleplay scenarios

    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
     justamente
    -0.08
    ints
    -0.07
    智
    -0.07
     Citation
    -0.07
    Citation
    -0.07
    试
    -0.07
     cak
    -0.07
    „
    -0.07
     Her
    -0.07
     „
    -0.07
    POSITIVE LOGITS
    ন্ন
    0.09
    -к
    0.08
    ONENT
    0.08
     følgende
    0.07
    Прод
    0.07
    ান
    0.07
     disso
    0.07
    ereg
    0.07
    স্থান
    0.07
     devam
    0.07
    Activations Density 0.010%

    No Known Activations