© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112657
    Prev
    Next
    INDEX
    Explanations

    negativity

    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
    _chart
    -0.08
    .п
    -0.08
     అభ
    -0.08
     carve
    -0.07
     malas
    -0.07
     Continued
    -0.07
     gezegd
    -0.07
    ñe
    -0.07
    .Info
    -0.07
    .coordinates
    -0.07
    POSITIVE LOGITS
     constantly
    0.10
     complaints
    0.10
    不断
    0.09
     constantemente
    0.09
     приходится
    0.09
    los
    0.08
     constamment
    0.08
     постоянно
    0.08
     এত
    0.08
     ständig
    0.08
    Activations Density 0.081%

    No Known Activations