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. 104047
    Prev
    Next
    INDEX
    Explanations

    ^

    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
     проверки
    -0.08
    кие
    -0.08
    .size
    -0.08
     mull
    -0.08
    .obj
    -0.07
     canon
    -0.07
    илл
    -0.07
    -stat
    -0.07
    	obj
    -0.07
     mann
    -0.07
    POSITIVE LOGITS
    'au
    0.08
     Hosp
    0.08
     lokal
    0.08
    Activator
    0.07
    akc
    0.07
    Asc
    0.07
    Exec
    0.07
     appréci
    0.07
     dhu
    0.07
     mezzo
    0.07
    Activations Density 0.033%

    No Known Activations