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. 29879
    Prev
    Next
    INDEX
    Explanations

    opened

    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
    feat
    -0.09
     formação
    -0.08
     contexts
    -0.08
     narrowly
    -0.08
     feats
    -0.08
    与你
    -0.08
    율
    -0.08
    nde
    -0.07
     opgebouwd
    -0.07
     feat
    -0.07
    POSITIVE LOGITS
     Stopwatch
    0.10
     initially
    0.09
     simultaneously
    0.09
    开始
    0.08
    Initially
    0.08
    Initi
    0.08
     શરૂ
    0.08
    试听
    0.08
    (wait
    0.08
    _WAIT
    0.08
    Activations Density 0.012%

    No Known Activations