© 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. 23-RESID-POST-AA
    11. 49592
    Prev
    Next
    INDEX
    Explanations

    Kosher recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sailing
    -0.08
     없이
    -0.08
     اليد
    -0.08
     �
    -0.08
     Aden
    -0.08
    沒有
    -0.08
     worthwhile
    -0.07
    WEST
    -0.07
     slipping
    -0.07
     atitude
    -0.07
    POSITIVE LOGITS
    metik
    0.11
    mos
    0.11
    her
    0.11
    cius
    0.09
    zt
    0.09
    sover
    0.09
    zta
    0.08
    anke
    0.08
    ovar
    0.08
    rae
    0.08
    Activations Density 0.002%

    No Known Activations