© 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. 78889
    Prev
    Next
    INDEX
    Explanations

    climate change

    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
     specializes
    -0.09
     teamwork
    -0.08
    voice
    -0.08
     prend
    -0.08
    IUnknown
    -0.08
     innocence
    -0.08
    üb
    -0.07
     Salvation
    -0.07
    Func
    -0.07
     specialize
    -0.07
    POSITIVE LOGITS
     increased
    0.12
     heightened
    0.11
     altered
    0.11
     Increased
    0.11
     exacerb
    0.11
     increase
    0.10
     증가
    0.10
     increases
    0.10
     altering
    0.10
     exacer
    0.10
    Activations Density 0.015%

    No Known Activations