© 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. 11-RESID-POST-AA
    11. 774
    Prev
    Next
    INDEX
    Explanations

    Biblical genealogy (Cain, Ham)

    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
    Minn
    -0.10
     Stück
    -0.09
    Suspend
    -0.08
     gerçekleştir
    -0.08
     prerequisites
    -0.08
     Booster
    -0.08
     Procedures
    -0.08
     Procedure
    -0.08
     Vorge
    -0.08
     typedef
    -0.08
    POSITIVE LOGITS
     impartial
    0.08
     noisy
    0.08
     violent
    0.08
     streak
    0.07
     incorrect
    0.07
     संघर्ष
    0.07
     nois
    0.07
    -winning
    0.07
     �
    0.07
     economics
    0.07
    Activations Density 0.002%

    No Known Activations