© 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. 71229
    Prev
    Next
    INDEX
    Explanations

    liking something

    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
     habl
    -0.08
    ();
    -0.08
     algunos
    -0.08
     البعض
    -0.08
    ()["
    -0.08
     الأه
    -0.08
     Implant
    -0.08
    gmail
    -0.08
     GCSE
    -0.07
    -visible
    -0.07
    POSITIVE LOGITS
     magic
    0.08
    107
    0.07
     ای
    0.07
     genre
    0.07
    सँग
    0.07
     movies
    0.07
     differentiated
    0.07
     flavor
    0.07
     exotic
    0.07
     اي
    0.07
    Activations Density 0.025%

    No Known Activations