© 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. 30153
    Prev
    Next
    INDEX
    Explanations

    liberal

    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
     stationed
    -0.08
     이용
    -0.08
    Dav
    -0.08
     snee
    -0.08
    lees
    -0.08
     evita
    -0.07
    被冻结
    -0.07
    �
    -0.07
     أب
    -0.07
     Cena
    -0.07
    POSITIVE LOGITS
    acy
    0.08
    -bodied
    0.08
    泛
    0.08
    -minded
    0.07
     monetary
    0.07
     flourish
    0.07
     instituted
    0.07
    財
    0.07
     prosperity
    0.07
     Sherman
    0.07
    Activations Density 0.003%

    No Known Activations