© 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. 3-RESID-POST-AA
    11. 3103
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kket
    -0.08
    HOR
    -0.08
    ක්
    -0.08
    gul
    -0.08
     democratic
    -0.08
    에서도
    -0.07
    onth
    -0.07
    hait
    -0.07
     ghi
    -0.07
    提醒
    -0.07
    POSITIVE LOGITS
     scales
    0.09
     pe
    0.08
    Thr
    0.08
    Prefer
    0.07
    Tan
    0.07
     stab
    0.07
    Yu
    0.07
    py
    0.07
    Cisco
    0.07
     complicated
    0.07
    Activations Density 0.002%

    No Known Activations