© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97377
    Prev
    Next
    INDEX
    Explanations

    Arabic text

    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
    -than
    -0.08
     XII
    -0.07
     avanti
    -0.07
     dài
    -0.07
    velocity
    -0.07
     druge
    -0.07
     perpetual
    -0.07
    đenja
    -0.07
     angla
    -0.07
     tertiary
    -0.07
    POSITIVE LOGITS
    وفر
    0.20
    احة
    0.19
    وف
    0.16
    اح
    0.16
    وافق
    0.13
    احات
    0.13
    واجد
    0.12
    واف
    0.12
    واج
    0.11
    提供
    0.10
    Activations Density 0.001%

    No Known Activations