© 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. 11-RESID-POST-AA
    11. 71031
    Prev
    Next
    INDEX
    Explanations

    Vertigo

    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
     expenditures
    -0.08
     legalization
    -0.08
     warmed
    -0.08
     legalized
    -0.08
     hardened
    -0.08
     prostitution
    -0.08
     hash
    -0.07
     cooled
    -0.07
     warms
    -0.07
     exits
    -0.07
    POSITIVE LOGITS
     dizzy
    0.11
     unsettling
    0.09
     सपना
    0.08
     persecut
    0.08
     dizziness
    0.08
     quest
    0.08
    ügen
    0.08
    161
    0.08
    .dtd
    0.08
     Sak
    0.08
    Activations Density 0.003%

    No Known Activations