© 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. 114052
    Prev
    Next
    INDEX
    Explanations

    zombie

    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
     Litt
    -0.09
    pricht
    -0.08
    making
    -0.08
     Born
    -0.08
     Palacio
    -0.08
     Bande
    -0.08
     معامل
    -0.08
     PIE
    -0.07
     UAE
    -0.07
     Palais
    -0.07
    POSITIVE LOGITS
     undead
    0.11
     apocalypse
    0.11
     zombie
    0.10
     Zombie
    0.09
    /AIDS
    0.09
    �
    0.09
     corpse
    0.09
     Infection
    0.08
    病毒
    0.08
    Zombie
    0.08
    Activations Density 0.003%

    No Known Activations