© 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. 78869
    Prev
    Next
    INDEX
    Explanations

    Climate change, limiting warming

    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
     rekl
    -0.08
     Appeal
    -0.08
     appeal
    -0.08
     mails
    -0.07
     versatile
    -0.07
    antics
    -0.07
    Perspective
    -0.07
     appeals
    -0.07
     complex
    -0.07
    irection
    -0.07
    POSITIVE LOGITS
     daqui
    0.11
     达
    0.10
     будущ
    0.09
     Planned
    0.09
     челов
    0.09
     sobri
    0.09
    东京
    0.09
     нынеш
    0.09
     لږ
    0.08
     чов
    0.08
    Activations Density 0.011%

    No Known Activations