© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6102
    Prev
    Next
    INDEX
    Explanations

    ReLU activation function

    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
     Schwarzen
    -0.09
    USSION
    -0.08
    ukkit
    -0.08
    .datetime
    -0.08
    Wiki
    -0.08
    .W
    -0.08
     તારીખ
    -0.08
    .Callback
    -0.08
    Cape
    -0.08
    .RUNTIME
    -0.08
    POSITIVE LOGITS
     rel
    0.17
     le
    0.16
     elu
    0.15
     REL
    0.14
     Le
    0.14
    Le
    0.14
     EL
    0.14
     Rel
    0.13
    .relu
    0.13
    Rel
    0.13
    Activations Density 0.001%

    No Known Activations