© 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. 108666
    Prev
    Next
    INDEX
    Explanations

    solo

    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
     meadow
    -0.07
     bush
    -0.07
     sediment
    -0.07
     sway
    -0.07
     certainty
    -0.07
     herd
    -0.07
     sacred
    -0.07
    mie
    -0.07
    eria
    -0.07
     vork
    -0.06
    POSITIVE LOGITS
    Hop
    0.07
    oidal
    0.07
    Harmony
    0.07
    🏼
    0.07
     продаж
    0.07
    BJ
    0.07
     �
    0.07
     versed
    0.07
     exc
    0.07
     Fos
    0.07
    Activations Density 0.004%

    No Known Activations