© 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 EvalsExportsinterp-engineNEWAPI 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. 18617
    Prev
    Next
    INDEX
    Explanations

    Builder

    np_max-act-logits · gemini-2.0-flash
    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
     או
    -0.08
     steig
    -0.08
     അല്ല
    -0.08
     அல்லது
    -0.08
     లేదా
    -0.08
     или
    -0.08
     characteristics
    -0.08
     ਜਾਂ
    -0.08
     несмотря
    -0.08
     немесе
    -0.08
    POSITIVE LOGITS
    એક
    0.08
    .All
    0.08
    idental
    0.08
    .Direct
    0.08
    кап
    0.08
    एक
    0.08
     allemaal
    0.08
    .Be
    0.08
    ەم
    0.08
    анс
    0.08
    Activations Density 0.001%

    No Known Activations