© 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. 103050
    Prev
    Next
    INDEX
    Explanations

    time

    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
     руб
    -0.08
     ұсыны
    -0.08
    SUPPORTED
    -0.08
     الأف
    -0.07
    /domain
    -0.07
     quarterly
    -0.07
     بها
    -0.07
    Supported
    -0.07
    شرة
    -0.07
    _digits
    -0.07
    POSITIVE LOGITS
     Zeitpunkt
    0.19
     timing
    0.17
     tidspunkt
    0.17
     timeline
    0.17
     arrival
    0.16
     Timing
    0.16
     timings
    0.16
     സമയ
    0.15
     elapsed
    0.15
     synchronization
    0.15
    Activations Density 0.039%

    No Known Activations