© 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. 63182
    Prev
    Next
    INDEX
    Explanations

    mafia

    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
     Cosmic
    -0.09
     обзор
    -0.08
    _Widget
    -0.08
    ileo
    -0.08
     Astronomy
    -0.08
     widget
    -0.08
    Bezier
    -0.08
    -animation
    -0.08
     Cartesian
    -0.08
     allerg
    -0.08
    POSITIVE LOGITS
     gangster
    0.15
     cocaine
    0.14
     mafia
    0.14
     clandest
    0.14
     Mafia
    0.12
     cartel
    0.12
     prostitutes
    0.11
     criminal
    0.11
     thug
    0.11
     cunning
    0.11
    Activations Density 0.028%

    No Known Activations