© 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. 11-RESID-POST-AA
    11. 561
    Prev
    Next
    INDEX
    Explanations

    diesel injection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Gen
    -0.08
     محدود
    -0.08
     precar
    -0.08
    Bound
    -0.08
    _PROTO
    -0.08
     disclaim
    -0.08
     perdido
    -0.08
    限
    -0.07
     Cina
    -0.07
     carefree
    -0.07
    POSITIVE LOGITS
    komen
    0.09
     NT
    0.09
     رات
    0.08
    komt
    0.08
    alatan
    0.08
     opciones
    0.08
    _digest
    0.08
     aanb
    0.08
     الزيت
    0.08
     kwargs
    0.08
    Activations Density 0.002%

    No Known Activations