© 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. 110912
    Prev
    Next
    INDEX
    Explanations

    security

    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
     Turbo
    -0.08
     Schön
    -0.08
     Nan
    -0.08
     Nord
    -0.08
    -N
    -0.08
     impl
    -0.07
     назнач
    -0.07
     Enh
    -0.07
     Nano
    -0.07
     Vega
    -0.07
    POSITIVE LOGITS
     exerc
    0.08
    党中央
    0.08
     தேசிய
    0.08
     militar
    0.08
     mindful
    0.08
    Pref
    0.08
    posted
    0.08
    nique
    0.08
    posting
    0.08
    ної
    0.08
    Activations Density 0.002%

    No Known Activations