© 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. 95045
    Prev
    Next
    INDEX
    Explanations

    German

    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
    ನ್ನು
    -0.08
    achi
    -0.08
    ACHI
    -0.08
     mfe
    -0.08
    かわ
    -0.08
    MAG
    -0.07
     blows
    -0.07
    .mult
    -0.07
     hopeless
    -0.07
     വർ
    -0.07
    POSITIVE LOGITS
     ли
    0.11
     désormais
    0.09
     infatti
    0.08
    _clause
    0.08
     sprake
    0.08
     hum
    0.08
    -ils
    0.08
     Rahul
    0.08
     vast
    0.07
    (CL
    0.07
    Activations Density 0.032%

    No Known Activations