Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11601
    Prev
    Next
    INDEX
    Explanations

    space

    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
     lust
    -0.08
    _ENGINE
    -0.08
     Versand
    -0.08
    _engine
    -0.08
    .engine
    -0.08
     rambut
    -0.08
     Accountant
    -0.08
     хим
    -0.07
     allgemeinen
    -0.07
     Sänger
    -0.07
    POSITIVE LOGITS
    空间
    0.11
     공간
    0.10
     пространство
    0.10
     espacios
    0.10
     espaces
    0.10
    spaces
    0.10
     spaces
    0.09
     пространства
    0.09
     espaços
    0.09
     geschaffen
    0.08
    Activations Density 0.042%

    No Known Activations