© 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. 24608
    Prev
    Next
    INDEX
    Explanations

    .

    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
    TY
    -0.08
    Variant
    -0.07
     variant
    -0.07
    Latin
    -0.07
     vibrant
    -0.07
     +/-
    -0.07
     many
    -0.07
     ±
    -0.07
     brincar
    -0.07
    -0.07
    POSITIVE LOGITS
     assinatura
    0.10
     déan
    0.10
     실시
    0.10
     준비
    0.09
     elaboración
    0.09
     Achter
    0.09
     તૈયાર
    0.09
     तैयार
    0.09
     gukora
    0.09
     담당
    0.08
    Activations Density 0.028%

    No Known Activations