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. 105974
    Prev
    Next
    INDEX
    Explanations

    feeling

    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
     cometido
    -0.09
     बच्च
    -0.08
    ree
    -0.08
     القانون
    -0.08
     Dritt
    -0.08
     mulighed
    -0.08
     કારણ
    -0.08
     recorrer
    -0.08
    ใบ
    -0.08
     सब
    -0.08
    POSITIVE LOGITS
     upbeat
    0.09
     beat
    0.08
    _plus
    0.08
     slump
    0.08
     FAT
    0.08
     succ
    0.08
     inclin
    0.08
    佳
    0.07
    Beat
    0.07
    _aux
    0.07
    Activations Density 0.009%

    No Known Activations