© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2622
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refractory
    -0.08
     otorg
    -0.08
     úgy
    -0.08
    น้ำ
    -0.07
     Republik
    -0.07
    ाती
    -0.07
     utmost
    -0.07
     berr
    -0.07
    ój
    -0.07
     Gerald
    -0.07
    POSITIVE LOGITS
     ART
    0.08
    ilty
    0.08
     geographic
    0.07
     Cox
    0.07
    0.07
     EURO
    0.07
     trivia
    0.07
    Indexed
    0.07
    .LAZY
    0.06
    :+
    0.06
    Activations Density 0.013%

    No Known Activations