© 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. 6610
    Prev
    Next
    INDEX
    Explanations

    tunnel

    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
     regalar
    -0.09
     jersey
    -0.09
     linge
    -0.09
    -0.09
     appointments
    -0.09
     mariage
    -0.09
     jerseys
    -0.08
    erseys
    -0.08
    Appointment
    -0.08
     appoint
    -0.08
    POSITIVE LOGITS
     tunnel
    0.33
     tunnels
    0.33
     Tunnel
    0.31
     subterr
    0.31
     underground
    0.31
    Tunnel
    0.29
     tunn
    0.28
    地下
    0.28
     тун
    0.27
     tunne
    0.26
    Activations Density 0.109%
    No Known Activations