© 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. 65025
    Prev
    Next
    INDEX
    Explanations

    Western blot

    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
    iają
    -0.08
    ><!--
    -0.08
     immutable
    -0.08
    Occupied
    -0.08
     rewind
    -0.07
     lawmakers
    -0.07
    ेशक
    -0.07
     strøm
    -0.07
     bedroom
    -0.07
     tomando
    -0.07
    POSITIVE LOGITS
     assays
    0.11
     PCR
    0.09
    PCR
    0.09
    -PCR
    0.09
     Kreuz
    0.08
     pruebas
    0.08
     spectroscopy
    0.08
     Verfahren
    0.08
     conducted
    0.08
     durchgeführt
    0.08
    Activations Density 0.005%

    No Known Activations