© 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. 19-RESID-POST-AA
    11. 102716
    Prev
    Next
    INDEX
    Explanations

    technique

    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
     Hosted
    -0.09
    Hosted
    -0.08
    .crypto
    -0.08
     Scenario
    -0.08
     refeições
    -0.08
     hosted
    -0.08
     cortisol
    -0.07
    abut
    -0.07
    Scenario
    -0.07
     Fitbit
    -0.07
    POSITIVE LOGITS
     techniques
    0.25
     technique
    0.24
     técnicas
    0.23
     technieken
    0.23
     Techniques
    0.23
    技巧
    0.22
     técnica
    0.22
    Technique
    0.22
     Technique
    0.22
     techniek
    0.20
    Activations Density 0.087%

    No Known Activations