© 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. 11-RESID-POST-AA
    11. 94467
    Prev
    Next
    INDEX
    Explanations

    sublime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    こ
    -0.08
    ostos
    -0.08
    θο
    -0.08
     estudio
    -0.08
    Scratch
    -0.08
    -0.07
     cohort
    -0.07
    artifact
    -0.07
     étude
    -0.07
    zta
    -0.07
    POSITIVE LOGITS
     Wee
    0.08
    �
    0.07
     electr
    0.07
    高度
    0.07
     nectar
    0.07
     reck
    0.07
     شیر
    0.07
     তথ
    0.07
     bully
    0.07
     ää
    0.07
    Activations Density 0.001%
    No Known Activations