© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112512
    Prev
    Next
    INDEX
    Explanations

    triggering events

    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
     Minerals
    -0.08
    eming
    -0.08
    -fed
    -0.08
     જોકે
    -0.07
    .Fe
    -0.07
    .cmd
    -0.07
    _IM
    -0.07
    _SY
    -0.07
    ngr
    -0.07
    (IM
    -0.07
    POSITIVE LOGITS
     investigations
    0.09
     investigaciones
    0.09
     réflexion
    0.09
     controversy
    0.09
     discussions
    0.09
     curiosity
    0.09
     investigation
    0.09
    立即
    0.09
     artific
    0.08
     goodwill
    0.08
    Activations Density 0.034%

    No Known Activations