© 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. 63242
    Prev
    Next
    INDEX
    Explanations

    Reminiscing or recalling past events

    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
     secrecy
    -0.08
    .minus
    -0.08
    enance
    -0.08
    PTS
    -0.08
    PAT
    -0.08
    anin
    -0.08
    agse
    -0.08
     derfor
    -0.07
     barrier
    -0.07
     يحتاج
    -0.07
    POSITIVE LOGITS
    ?</
    0.16
    ？
    0.14
    ？」
    0.14
    ？↵↵
    0.13
    ؟
    0.13
    ？」↵
    0.13
    ?",
    0.13
    吗
    0.13
    ?↵↵↵↵
    0.13
    ？↵
    0.12
    Activations Density 0.095%

    No Known Activations