© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77809
    Prev
    Next
    INDEX
    Explanations

    ROM or memory

    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
     sangu
    -0.09
     liens
    -0.09
     estren
    -0.09
     despr
    -0.09
    cession
    -0.08
     lien
    -0.08
     pey
    -0.08
     viol
    -0.08
     sostenible
    -0.08
     pasaj
    -0.08
    POSITIVE LOGITS
     diode
    0.12
     storing
    0.11
     памяти
    0.10
     EEPROM
    0.10
     Memory
    0.09
     capacit
    0.09
    Memory
    0.09
    忆
    0.09
     stor
    0.09
     capacitor
    0.09
    Activations Density 0.006%

    No Known Activations