© 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 EvalsExportsAPI 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. 49485
    Prev
    Next
    INDEX
    Explanations

    مرت

    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
    trica
    -0.08
    oche
    -0.08
    Rw
    -0.08
    Cr
    -0.08
    taste
    -0.07
     Cr
    -0.07
    tron
    -0.07
    landır
    -0.07
    ್ರ
    -0.07
     liked
    -0.07
    POSITIVE LOGITS
    ديات
    0.11
    فاع
    0.11
    دي
    0.11
    بط
    0.10
    دل
    0.09
    دى
    0.09
    فع
    0.09
    كب
    0.09
    دية
    0.09
    َق
    0.09
    Activations Density 0.006%

    No Known Activations