© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18802
    Prev
    Next
    INDEX
    Explanations

    markers and sentinels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unga
    -0.08
     pertinente
    -0.08
    ubo
    -0.07
     ráp
    -0.07
     sped
    -0.07
     gewonnen
    -0.07
    bringing
    -0.07
     атрым
    -0.07
     مباش
    -0.07
     fundamentals
    -0.07
    POSITIVE LOGITS
     sentinel
    0.26
     marker
    0.26
     markers
    0.25
    _marker
    0.24
    Marker
    0.23
    特殊
    0.22
    marker
    0.22
     special
    0.22
     Marker
    0.21
    -marker
    0.21
    Activations Density 0.043%

    No Known Activations