© 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. 50510
    Prev
    Next
    INDEX
    Explanations

    �

    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
     facilité
    -0.08
     surn
    -0.08
     acne
    -0.08
     kautta
    -0.08
    _MINOR
    -0.08
     adventure
    -0.08
     साह
    -0.07
     Adventure
    -0.07
    _PART
    -0.07
     apnea
    -0.07
    POSITIVE LOGITS
    ＊＊＊＊
    0.11
    ▀
    0.11
    �
    0.11
    ************************
    0.10
    ────────────────
    0.10
    �
    0.10
    ********
    0.10
    613
    0.10
    ━
    0.10
    �
    0.10
    Activations Density 0.001%

    No Known Activations