© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    Q

    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
     exorbit
    -0.08
    /API
    -0.08
     founders
    -0.08
    IBIL
    -0.08
     TEC
    -0.08
    илә
    -0.08
    Angela
    -0.08
     shocks
    -0.08
     ਪ੍ਰ
    -0.07
    ендәге
    -0.07
    POSITIVE LOGITS
     purple
    0.08
     Palo
    0.07
    Purple
    0.07
    122
    0.07
    vand
    0.07
    unc
    0.07
     Hausa
    0.07
    微信群
    0.07
    pand
    0.07
    purple
    0.07
    Activations Density 0.002%

    No Known Activations