© 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. 47408
    Prev
    Next
    INDEX
    Explanations

    ogen

    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
    nous
    -0.08
     Douglas
    -0.08
     NEC
    -0.07
    ：(
    -0.07
     grounded
    -0.07
    ivid
    -0.07
    odont
    -0.07
    Parking
    -0.07
    ：（
    -0.07
    ahat
    -0.07
    POSITIVE LOGITS
     replenish
    0.18
     depleted
    0.18
     replen
    0.18
     depletion
    0.17
     dwind
    0.13
     deficits
    0.12
    不足
    0.11
     reserves
    0.11
     부족
    0.11
     exhausted
    0.10
    Activations Density 0.012%

    No Known Activations