© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108755
    Prev
    Next
    INDEX
    Explanations

    Medical tests/confirmations

    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
     relatable
    -0.08
     गत
    -0.08
     overhe
    -0.08
     visible
    -0.08
     vents
    -0.08
     relational
    -0.08
     emitting
    -0.08
     tí
    -0.07
     dynamically
    -0.07
     despr
    -0.07
    POSITIVE LOGITS
     подоз
    0.12
     সন্দ
    0.12
     sospe
    0.11
     suspicion
    0.11
     তদন্ত
    0.10
     vervolg
    0.10
     검사
    0.10
     verdachte
    0.10
     durchgeführt
    0.10
     suspicious
    0.10
    Activations Density 0.013%

    No Known Activations