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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48075
    Prev
    Next
    INDEX
    Explanations

    code and foreign languages

    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
    080
    -0.08
     насос
    -0.08
    altungen
    -0.07
    STYLE
    -0.07
     kron
    -0.07
    VK
    -0.07
    ide
    -0.07
     werk
    -0.07
    -con
    -0.07
     uku
    -0.07
    POSITIVE LOGITS
     yoo
    0.08
    'électricité
    0.08
     Ẹ
    0.08
    .destroy
    0.08
     Bi
    0.08
     Erklärung
    0.08
    ,len
    0.07
     ஜ
    0.07
     JObject
    0.07
     Questo
    0.07
    Activations Density 0.001%

    No Known Activations