© 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. 114300
    Prev
    Next
    INDEX
    Explanations

    memory order

    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
    REDIT
    -0.08
    idzwa
    -0.08
     alfabet
    -0.08
    ையே
    -0.08
     ಅಲ್ಲ
    -0.08
     adapting
    -0.08
    redit
    -0.07
     ironing
    -0.07
    รั่ง
    -0.07
    Algo
    -0.07
    POSITIVE LOGITS
     espac
    0.08
     Cascade
    0.08
     Refer
    0.08
     pagi
    0.08
     Mondays
    0.08
     Fired
    0.08
     Beam
    0.08
     Bier
    0.08
     Lite
    0.07
     ذهن
    0.07
    Activations Density 0.000%

    No Known Activations