© 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. 29114
    Prev
    Next
    INDEX
    Explanations

    each

    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
    -offs
    -0.08
     अनुस
    -0.08
     progresses
    -0.08
    wona
    -0.08
     Ce
    -0.08
     instincts
    -0.07
    sweet
    -0.07
    Ce
    -0.07
    lossene
    -0.07
     mixes
    -0.07
    POSITIVE LOGITS
     detected
    0.07
     найден
    0.07
     kolej
    0.07
     donnée
    0.07
     ATH
    0.07
     harbour
    0.07
     hush
    0.07
     wag
    0.07
    ага
    0.07
    kx
    0.07
    Activations Density 0.016%

    No Known Activations