© 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. 3049
    Prev
    Next
    INDEX
    Explanations

    bit

    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
    roof
    -0.08
    brite
    -0.08
     vink
    -0.08
    agraph
    -0.08
     مات
    -0.08
     TAK
    -0.08
     Kik
    -0.07
     Soto
    -0.07
     टो
    -0.07
     Chattanooga
    -0.07
    POSITIVE LOGITS
    war
    0.08
    _chunk
    0.08
     fue
    0.08
     commerce
    0.07
    War
    0.07
     activ
    0.07
    0.07
     establecimiento
    0.07
    <N
    0.07
     realloc
    0.07
    Activations Density 0.006%
    No Known Activations