© 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. 7-RESID-POST-AA
    11. 765
    Prev
    Next
    INDEX
    Explanations

    NPC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bünd
    -0.07
     النبات
    -0.07
    快
    -0.07
    위를
    -0.07
    /of
    -0.07
     Stil
    -0.07
     Volcano
    -0.07
     skil
    -0.07
    �
    -0.07
    বান
    -0.07
    POSITIVE LOGITS
     Morris
    0.07
     Bella
    0.07
     governments
    0.07
     तर
    0.07
    Fem
    0.07
     Governments
    0.07
     Ramsey
    0.07
     tens
    0.07
    .support
    0.07
     Dreams
    0.07
    Activations Density 0.002%

    No Known Activations