© 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. 50027
    Prev
    Next
    INDEX
    Explanations

    say "8"

    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
    PT
    -0.08
    acceler
    -0.08
    db
    -0.08
    Ingreso
    -0.08
    inon
    -0.08
     kinder
    -0.08
     accelerate
    -0.08
    in
    -0.08
    pt
    -0.07
     abst
    -0.07
    POSITIVE LOGITS
     Magazine
    0.09
     fotógrafo
    0.09
    239
    0.09
     Cont
    0.09
     Photography
    0.09
     magni
    0.08
     Een
    0.08
     photographer
    0.08
     Camera
    0.08
     Collector
    0.08
    Activations Density 0.000%

    No Known Activations