© 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. 78410
    Prev
    Next
    INDEX
    Explanations

    research and studies

    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
    igan
    -0.07
    oid
    -0.07
    �
    -0.07
    yclic
    -0.07
    ज
    -0.07
    jective
    -0.07
    ্ড
    -0.07
     −
    -0.07
    gehör
    -0.07
     тран
    -0.07
    POSITIVE LOGITS
     similarly
    0.10
     ähnlich
    0.10
     тоже
    0.10
     równie
    0.09
     semelhantes
    0.09
     OUR
    0.09
     pareil
    0.09
     इसी
    0.08
     BUR
    0.08
     такими
    0.08
    Activations Density 0.203%

    No Known Activations