© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20677
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certain
    -0.08
    گذ
    -0.07
    նելու
    -0.07
    սկ
    -0.07
    ებლის
    -0.07
    ացնելու
    -0.07
    վելու
    -0.07
    ising
    -0.07
    XXXX
    -0.07
     վերահ
    -0.07
    POSITIVE LOGITS
     కానీ
    0.12
     પરંતુ
    0.10
     wobei
    0.10
     જેમાં
    0.10
     همچنین
    0.10
    。また
    0.10
     이는
    0.10
    。ただ
    0.10
     जिसमें
    0.10
     ಆದರೆ
    0.09
    Activations Density 0.007%

    No Known Activations