© 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. 11-RESID-POST-AA
    11. 65353
    Prev
    Next
    INDEX
    Explanations

    daily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Binary
    -0.08
    Directive
    -0.08
     समाप्त
    -0.07
     terminate
    -0.07
    Vend
    -0.07
    Final
    -0.07
     Directive
    -0.07
    Proper
    -0.07
     reac
    -0.07
    Terminate
    -0.07
    POSITIVE LOGITS
     quotidienne
    0.15
     quotidien
    0.15
     quotid
    0.14
     everyday
    0.14
     தின
    0.14
     günlük
    0.13
     दैनिक
    0.12
     cotidiana
    0.12
     ежеднев
    0.12
     täglichen
    0.12
    Activations Density 0.029%

    No Known Activations