© 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. 23-RESID-POST-AA
    11. 49688
    Prev
    Next
    INDEX
    Explanations

    say "n" ending

    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
    =N
    -0.09
     N
    -0.09
     leef
    -0.09
    \":
    -0.09
    \,
    -0.08
    \">\
    -0.08
    ues
    -0.08
    =start
    -0.08
    =\"
    -0.08
    ific
    -0.08
    POSITIVE LOGITS
    Interrupted
    0.16
    Cancelled
    0.13
    Canceled
    0.13
    Good
    0.13
    Bye
    0.12
    Ex
    0.12
    Operation
    0.11
     Interrupted
    0.11
     interrupted
    0.11
     canceled
    0.10
    Activations Density 0.002%

    No Known Activations