© 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. 23-RESID-POST-AA
    11. 51756
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ]↵
    -0.10
    /)↵
    -0.09
    ,)↵
    -0.09
    ']↵
    -0.09
    Really
    -0.09
    /')↵
    -0.09
     eben
    -0.09
     exclusivement
    -0.08
     ])↵
    -0.08
     //}↵
    -0.08
    POSITIVE LOGITS
     những
    0.14
    但
    0.11
     once
    0.10
     alene
    0.10
    เพ
    0.10
    光
    0.09
    但是
    0.08
     nejen
    0.08
    trs
    0.08
    ably
    0.08
    Activations Density 0.004%

    No Known Activations