© 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. 64590
    Prev
    Next
    INDEX
    Explanations

    2

    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
     agriculture
    -0.09
    /movie
    -0.08
    ÷
    -0.08
     greg
    -0.08
     tess
    -0.08
     esport
    -0.08
    เท
    -0.08
     agrícolas
    -0.08
     hrane
    -0.07
     brochures
    -0.07
    POSITIVE LOGITS
     penalties
    0.11
     penal
    0.10
     penalty
    0.10
    Penalty
    0.09
    怒
    0.08
    .constraint
    0.08
     штраф
    0.08
     minimized
    0.08
     squared
    0.08
    .constraints
    0.08
    Activations Density 0.036%

    No Known Activations