© 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 EvalsExportsAPI 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. 63803
    Prev
    Next
    INDEX
    Explanations

    Buddy

    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
     receptive
    -0.08
     bim
    -0.07
     Junta
    -0.07
    oons
    -0.07
     similarity
    -0.07
     negatively
    -0.07
     quake
    -0.07
     ingenuity
    -0.07
     creatively
    -0.07
     Brest
    -0.07
    POSITIVE LOGITS
     installing
    0.08
    .install
    0.08
    aga
    0.08
     erreurs
    0.08
    താണ്
    0.08
     今日
    0.08
    abox
    0.07
    タグ
    0.07
    gross
    0.07
    .lbl
    0.07
    Activations Density 0.000%

    No Known Activations