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. 8483
    Prev
    Next
    INDEX
    Explanations

    cannot/full (error states)

    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
     মধ্য
    -0.08
    账
    -0.08
    شف
    -0.08
    .Nullable
    -0.08
    isia
    -0.07
     positiv
    -0.07
     Baud
    -0.07
     transcript
    -0.07
    iverse
    -0.07
     haunting
    -0.07
    POSITIVE LOGITS
     overcrow
    0.11
     Capacity
    0.11
    _capacity
    0.11
    Capacity
    0.11
     capacity
    0.10
     क्षमता
    0.10
     overflow
    0.10
     Overflow
    0.10
    .capacity
    0.10
    限制
    0.10
    Activations Density 0.010%

    No Known Activations