© 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. 44771
    Prev
    Next
    INDEX
    Explanations

    seasoning with

    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
     नेटवर्क
    -0.08
     museum
    -0.07
     uintptr
    -0.07
     ਉ
    -0.07
     ds
    -0.07
     gradual
    -0.07
    ógicos
    -0.07
     pointed
    -0.07
     ਪਰ
    -0.07
     faktisk
    -0.07
    POSITIVE LOGITS
    เลือก
    0.08
     hazırlan
    0.08
    �
    0.08
    ={`
    0.08
     rehearsal
    0.08
     بالج
    0.08
    harga
    0.08
     beforehand
    0.07
     trump
    0.07
    tanggal
    0.07
    Activations Density 0.010%

    No Known Activations