© 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. 47115
    Prev
    Next
    INDEX
    Explanations

    art

    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
     preferably
    -0.08
     заранее
    -0.08
     nicer
    -0.08
     회원
    -0.08
     풀
    -0.08
    -sm
    -0.08
    (sm
    -0.08
     minim
    -0.08
     capabilities
    -0.07
    .Selected
    -0.07
    POSITIVE LOGITS
     societies
    0.12
    Religion
    0.11
     weltweit
    0.10
     centuries
    0.10
     civilizations
    0.09
     museum
    0.09
     century
    0.09
     Europe's
    0.09
    Europe
    0.09
     wereldwijd
    0.09
    Activations Density 0.040%

    No Known Activations