© 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. 96767
    Prev
    Next
    INDEX
    Explanations

    Gauges and sensors

    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
     Veranstaltungen
    -0.09
     enterr
    -0.09
     ઉપયોગ
    -0.09
     Unterricht
    -0.08
     Ferien
    -0.08
    窝
    -0.08
     משתמש
    -0.08
     parkeren
    -0.08
     장소
    -0.08
     tổ
    -0.08
    POSITIVE LOGITS
     gauges
    0.16
     indicators
    0.14
     sensors
    0.14
     monitors
    0.14
     instruments
    0.14
     diagnostics
    0.14
     readings
    0.14
     indicadores
    0.13
     indicator
    0.13
    ensors
    0.13
    Activations Density 0.034%

    No Known Activations