© 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. 50355
    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
     jou
    -0.09
     cv
    -0.08
     salvo
    -0.08
     pekerjaan
    -0.07
    cv
    -0.07
    aur
    -0.07
    gro
    -0.07
     playing
    -0.07
    =cv
    -0.07
     wchar
    -0.07
    POSITIVE LOGITS
    үүд
    0.08
    _snapshot
    0.08
    สอบ
    0.08
     Unique
    0.08
    יכ
    0.07
    мом
    0.07
    Snapshot
    0.07
    .input
    0.07
    (snapshot
    0.07
     attrib
    0.07
    Activations Density 0.000%

    No Known Activations