© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 64898
    Prev
    Next
    INDEX
    Explanations

    game descriptions

    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
    얼
    -0.08
     Specifically
    -0.08
     Out
    -0.08
     However
    -0.08
    itive
    -0.07
    out
    -0.07
    	out
    -0.07
     eben
    -0.07
    .Out
    -0.07
     out
    -0.07
    POSITIVE LOGITS
    Nearby
    0.08
     forsø
    0.08
     récupération
    0.08
     snapped
    0.08
     карт
    0.08
     pern
    0.08
     leafy
    0.08
     snaps
    0.08
    Snapshot
    0.07
    回应
    0.07
    Activations Density 0.007%

    No Known Activations