© 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. 110996
    Prev
    Next
    INDEX
    Explanations

    ancient infrastructure

    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
     ಕಳೆದ
    -0.08
     unwrap
    -0.08
    ೊಬ್ಬ
    -0.08
    CEP
    -0.08
    Depuis
    -0.08
     wager
    -0.08
    headline
    -0.08
     bonus
    -0.08
    投注
    -0.07
    ಿಸುತ್ತ
    -0.07
    POSITIVE LOGITS
     ingenious
    0.12
     Gond
    0.10
     ingenuity
    0.10
     painstaking
    0.09
     cunning
    0.09
     craftsmen
    0.09
     craftsmanship
    0.09
     сооруж
    0.09
     Ingen
    0.09
     कृषि
    0.09
    Activations Density 0.012%

    No Known Activations