© 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. 3-RESID-POST-AA
    11. 2558
    Prev
    Next
    INDEX
    Explanations

    abundant

    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
    性质
    -0.08
     అలాగే
    -0.08
    )))↵↵
    -0.08
    ayer
    -0.07
    IER
    -0.07
    Gun
    -0.07
    -disable
    -0.07
    lok
    -0.07
     précis
    -0.07
    НА
    -0.07
    POSITIVE LOGITS
    862
    0.08
     incarceration
    0.08
     رب
    0.08
    .Contracts
    0.08
     goats
    0.08
     spacecraft
    0.08
     pne
    0.07
     чис
    0.07
     pneumatic
    0.07
     roca
    0.07
    Activations Density 0.004%

    No Known Activations