© 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 EvalsExportsinterp-engineNEWAPI 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. 111185
    Prev
    Next
    INDEX
    Explanations

    Dungeons and Dragons classes

    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
     slippery
    -0.09
    ാമ
    -0.09
    wiek
    -0.08
     slang
    -0.08
    coli
    -0.08
     econom
    -0.08
     schl
    -0.07
    ി
    -0.07
     nau
    -0.07
     slimme
    -0.07
    POSITIVE LOGITS
     righteousness
    0.11
     uplifting
    0.10
    Healing
    0.09
     covenant
    0.09
     పవ
    0.08
     combating
    0.08
     vow
    0.08
     добро
    0.08
     Reiki
    0.08
     righteous
    0.08
    Activations Density 0.009%

    No Known Activations