Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49052
    Prev
    Next
    INDEX
    Explanations

    Legal and financial documents

    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
    >Hello
    -0.07
    Genre
    -0.07
     melod
    -0.07
    )o
    -0.07
    Genres
    -0.07
    iciro
    -0.06
    Hdr
    -0.06
    Inicio
    -0.06
     greet
    -0.06
     sos
    -0.06
    POSITIVE LOGITS
     unavailable
    0.09
    .nc
    0.08
     steril
    0.07
    联系电话
    0.07
     onboard
    0.07
    收费
    0.07
     Lanz
    0.07
    ='../
    0.07
     Cru
    0.07
    0.07
    Activations Density 38.495%

    No Known Activations