© 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. 11-RESID-POST-AA
    11. 113663
    Prev
    Next
    INDEX
    Explanations

    Code testing

    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
     erschienen
    -0.08
     Pompe
    -0.07
     referring
    -0.07
     affiliated
    -0.07
     лечеб
    -0.07
    achine
    -0.07
    anko
    -0.07
    chini
    -0.07
    去了
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Incorrect
    0.10
     correctly
    0.10
    Incorrect
    0.10
     corretamente
    0.09
    Empty
    0.09
    _empty
    0.09
     Empty
    0.08
    (unittest
    0.08
     osnov
    0.08
     જ્યારે
    0.08
    Activations Density 0.005%

    No Known Activations