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

    Neuronpedia

    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. 103196
    Prev
    Next
    INDEX
    Explanations

    say "-a"

    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
    (Web
    -0.08
    (Random
    -0.07
     eigene
    -0.07
     şəkildə
    -0.07
     seiz
    -0.07
     incons
    -0.07
    یری
    -0.07
     autore
    -0.07
     собственной
    -0.07
    (www
    -0.07
    POSITIVE LOGITS
    –
    0.12
    −
    0.12
     -
    0.11
    -input
    0.10
     –
    0.10
    -ion
    0.10
    －
    0.10
    -location
    0.09
    -
    0.09
    -field
    0.09
    Activations Density 0.018%

    No Known Activations