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. 46889
    Prev
    Next
    INDEX
    Explanations

    handshakes

    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
    .layers
    -0.10
    	layer
    -0.09
    _layers
    -0.09
     layering
    -0.09
    .layer
    -0.08
     layers
    -0.08
    187
    -0.08
    _layer
    -0.08
     layer
    -0.08
     Layers
    -0.08
    POSITIVE LOGITS
     cumpr
    0.10
     handshake
    0.09
     яб
    0.09
    握
    0.09
     freundlich
    0.09
     greetings
    0.09
    бат
    0.08
     wag
    0.08
    атку
    0.08
    яб
    0.08
    Activations Density 0.004%

    No Known Activations