© 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. 64748
    Prev
    Next
    INDEX
    Explanations

    HTML overlay

    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
     resonance
    -0.09
    .doc
    -0.08
     categor
    -0.08
     the
    -0.08
     suitcase
    -0.07
    gt
    -0.07
     and
    -0.07
     Reson
    -0.07
     reson
    -0.07
    ,
    -0.07
    POSITIVE LOGITS
    .overlay
    0.15
     overlay
    0.15
    Overlay
    0.15
    -overlay
    0.15
    overlay
    0.15
    _overlay
    0.14
     Overlay
    0.14
     overlays
    0.14
    覆盖
    0.12
    罩
    0.12
    Activations Density 0.004%

    No Known Activations