© 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. 65324
    Prev
    Next
    INDEX
    Explanations

    Single letters

    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
     vivido
    -0.08
    廉
    -0.08
     realizada
    -0.08
     erne
    -0.07
     mil
    -0.07
     bege
    -0.07
     estrutur
    -0.07
     loc
    -0.07
    -0.07
     cares
    -0.07
    POSITIVE LOGITS
    �
    0.10
    ′
    0.09
    iffany
    0.08
    )]
    0.08
    .story
    0.08
    )],
    0.08
    )`
    0.08
    ″
    0.08
    inyin
    0.08
    story
    0.08
    Activations Density 0.107%
    No Known Activations