© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2800
    Prev
    Next
    INDEX
    Explanations

    wagging

    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
    comes
    -0.09
    yman
    -0.09
    assim
    -0.08
    come
    -0.08
    inel
    -0.08
     رح
    -0.08
     inne
    -0.07
    LEASE
    -0.07
    ém
    -0.07
    ZO
    -0.07
    POSITIVE LOGITS
     ub
    0.09
    ો
    0.08
     الفك
    0.08
     unpar
    0.08
    _ps
    0.08
     ;-)
    0.08
    UID
    0.08
     pu
    0.08
     coke
    0.08
     anam
    0.08
    Activations Density 0.004%

    No Known Activations