Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12741
    Prev
    Next
    INDEX
    Explanations

    throughput

    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
     Fix
    -0.07
    باط
    -0.07
    VNode
    -0.07
     revive
    -0.07
     admi
    -0.07
     denom
    -0.07
    葉
    -0.07
     adlı
    -0.07
     olduk
    -0.07
     stretchy
    -0.07
    POSITIVE LOGITS
     assays
    0.13
     batches
    0.11
     screening
    0.11
    筛
    0.10
    _batches
    0.10
     assay
    0.10
     mechan
    0.09
     cultures
    0.09
    _BATCH
    0.09
     Screening
    0.09
    Activations Density 0.005%

    No Known Activations