© 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. 91823
    Prev
    Next
    INDEX
    Explanations

    plotting code snippets

    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
    粉
    -0.08
     ethn
    -0.08
     지도
    -0.08
     ballots
    -0.08
     నాయక
    -0.08
     ته
    -0.07
     skies
    -0.07
    Flights
    -0.07
     Bird
    -0.07
     تص
    -0.07
    POSITIVE LOGITS
    oq
    0.08
    ्याम
    0.08
    ormat
    0.07
    curl
    0.07
     marco
    0.07
    vlo
    0.07
    ξ
    0.07
    reven
    0.07
    urnal
    0.07
     DISP
    0.07
    Activations Density 0.000%

    No Known Activations