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. 48583
    Prev
    Next
    INDEX
    Explanations

    injury

    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
     funeral
    -0.09
     يتم
    -0.08
     cocina
    -0.08
     laboratories
    -0.08
     countertop
    -0.08
     lavander
    -0.08
     obedient
    -0.08
     mortality
    -0.08
    .lab
    -0.08
     Paste
    -0.07
    POSITIVE LOGITS
     offseason
    0.08
     нерв
    0.08
     injuries
    0.08
    θ
    0.08
     चोट
    0.08
     неис
    0.08
    ξ
    0.08
     infamous
    0.08
     좀
    0.08
     rowspan
    0.08
    Activations Density 0.016%

    No Known Activations