© 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. 70542
    Prev
    Next
    INDEX
    Explanations

    color codes

    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
    便利
    -0.09
    унок
    -0.08
     Einrichtung
    -0.08
     gratis
    -0.08
     Metz
    -0.08
    Friendly
    -0.08
     서비스를
    -0.08
    -short
    -0.07
     Cupid
    -0.07
     Charm
    -0.07
    POSITIVE LOGITS
     darkness
    0.11
     darkest
    0.11
     darker
    0.09
    -dark
    0.09
     hide
    0.08
     hiding
    0.08
     sombre
    0.08
    暗
    0.08
     Darkness
    0.08
     severe
    0.08
    Activations Density 0.005%

    No Known Activations