© 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. 23-RESID-POST-AA
    11. 50951
    Prev
    Next
    INDEX
    Explanations

    goods

    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
    _scripts
    -0.09
     recepten
    -0.09
    _script
    -0.08
     Scripts
    -0.08
    orel
    -0.08
    _playlist
    -0.08
     беременности
    -0.07
     apnea
    -0.07
     Doyle
    -0.07
     Script
    -0.07
    POSITIVE LOGITS
     goods
    0.40
     goederen
    0.34
    goods
    0.34
    Goods
    0.33
     good
    0.32
    good
    0.31
    _goods
    0.31
    .goods
    0.31
     Goods
    0.30
    Good
    0.29
    Activations Density 0.065%

    No Known Activations