© 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. 129253
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    ']↵↵
    -0.08
    '].
    -0.08
     gyf
    -0.08
    ']['
    -0.08
     Tunes
    -0.08
     Shin
    -0.07
     Sudan
    -0.07
     Multi
    -0.07
     Camaro
    -0.07
     multi
    -0.07
    POSITIVE LOGITS
     wilt
    0.08
    ைக்
    0.08
     sead
    0.08
     ducks
    0.08
     مقصد
    0.08
    Embora
    0.08
    返回
    0.07
     בראש
    0.07
     bird
    0.07
     apparaten
    0.07
    Activations Density 0.007%

    No Known Activations