© 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. 29713
    Prev
    Next
    INDEX
    Explanations

    symbolism

    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
     fak
    -0.09
    ত্র
    -0.09
     সক্ষম
    -0.07
    ন্ট
    -0.07
     CPP
    -0.07
     Barack
    -0.07
     Ono
    -0.07
     Definition
    -0.07
    opolitan
    -0.07
    তি
    -0.07
    POSITIVE LOGITS
     symbolism
    0.20
    寓
    0.14
    意义
    0.13
     символ
    0.12
     meanings
    0.12
     symbolic
    0.11
     symbols
    0.11
     simb
    0.11
     imagery
    0.11
     alleg
    0.11
    Activations Density 0.034%

    No Known Activations