© 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. 23-RESID-POST-AA
    11. 51406
    Prev
    Next
    INDEX
    Explanations

    versions of "announced"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Puedes
    -0.13
     puedas
    -0.12
    Cada
    -0.11
     può
    -0.11
     your
    -0.11
     regardless
    -0.10
     puedes
    -0.10
     possam
    -0.10
     peuvent
    -0.10
     poate
    -0.10
    POSITIVE LOGITS
     anunció
    0.15
     בשנת
    0.15
     anunciou
    0.15
     anunciado
    0.14
     ανακοίν
    0.14
     publicó
    0.14
     huko
    0.13
     árið
    0.13
     lanzó
    0.13
     publicou
    0.13
    Activations Density 0.065%

    No Known Activations