© 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. 6673
    Prev
    Next
    INDEX
    Explanations

    say "fl or ов"

    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
     appointments
    -0.08
    atatables
    -0.07
     appet
    -0.07
     delivered
    -0.07
     תודה
    -0.07
     appointment
    -0.07
    kiss
    -0.07
     angst
    -0.07
     anxiety
    -0.07
     testimonials
    -0.07
    POSITIVE LOGITS
    OGA
    0.10
     Орган
    0.08
    这里
    0.07
    О
    0.07
     Скор
    0.07
    yoni
    0.07
     જણ
    0.07
    Ош
    0.07
     VX
    0.07
    aremos
    0.07
    Activations Density 0.000%

    No Known Activations