© 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. 44461
    Prev
    Next
    INDEX
    Explanations

    battery, ion

    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
     انت
    -0.08
    _ALIGN
    -0.08
     spanking
    -0.08
    ిస్ట
    -0.08
     público
    -0.08
     ఆన
    -0.08
     confidently
    -0.08
     hjemmes
    -0.08
     confident
    -0.07
     조회
    -0.07
    POSITIVE LOGITS
     batteries
    0.13
     rechargeable
    0.12
     аккумуля
    0.12
     батар
    0.11
    battery
    0.11
     Batteries
    0.11
     fuel
    0.10
    fuel
    0.10
    Fuel
    0.10
    Battery
    0.09
    Activations Density 0.010%

    No Known Activations