© 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. 15-RESID-POST-AA
    11. 16653
    Prev
    Next
    INDEX
    Explanations

    Non-English tokens

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -"
    -0.10
     "**
    -0.10
    (?:
    -0.09
    —including
    -0.09
    -like
    -0.08
    -/
    -0.08
     "":↵
    -0.08
    -period
    -0.08
    -associated
    -0.08
     använder
    -0.08
    POSITIVE LOGITS
    SU
    0.08
    否则
    0.08
    chern
    0.07
    akc
    0.07
    zył
    0.07
    áte
    0.07
    Implement
    0.07
    Dam
    0.07
    ecs
    0.07
    并
    0.07
    Activations Density 0.247%

    No Known Activations