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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 47904
    Prev
    Next
    INDEX
    Explanations

    horror and supernatural

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    世界杯
    -0.12
     Soccer
    -0.11
    球
    -0.11
     Brasil
    -0.10
     jersey
    -0.10
     спортсмен
    -0.10
     Adidas
    -0.10
     adidas
    -0.10
     Rocket
    -0.10
    “一带一路
    -0.10
    POSITIVE LOGITS
     paranormal
    0.22
     horror
    0.21
     eerie
    0.20
     haunted
    0.20
     mansion
    0.19
     creepy
    0.18
     terrified
    0.18
     attic
    0.18
     supernatural
    0.18
     Haunted
    0.18
    Activations Density 0.062%

    No Known Activations