© 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. 51413
    Prev
    Next
    INDEX
    Explanations

    مست

    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
     Divine
    -0.08
     divine
    -0.08
    ーブル
    -0.08
     elektric
    -0.08
    ball
    -0.07
     bourgeois
    -0.07
    541
    -0.07
     తీవ్ర
    -0.07
    rachten
    -0.07
     winning
    -0.07
    POSITIVE LOGITS
    ندا
    0.11
    فيض
    0.11
    ند
    0.10
    ندية
    0.09
    م
    0.08
    uhn
    0.08
    قی
    0.08
    ندس
    0.08
    ending
    0.08
     lupa
    0.08
    Activations Density 0.001%

    No Known Activations