© 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. 164
    Prev
    Next
    INDEX
    Explanations

    .concat

    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
     recruiting
    -0.09
    eda
    -0.09
    νό
    -0.09
     scarcity
    -0.08
     prosperity
    -0.08
     Kaiser
    -0.08
     computation
    -0.08
    icemail
    -0.07
     zun
    -0.07
     testoster
    -0.07
    POSITIVE LOGITS
     polygon
    0.08
     abstracts
    0.08
     PARAMETERS
    0.07
     NSArray
    0.07
     Vor
    0.07
    ించారు
    0.07
    ませ
    0.07
     Gespr
    0.07
    (['
    0.07
     previamente
    0.07
    Activations Density 0.001%

    No Known Activations