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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43874
    Prev
    Next
    INDEX
    Explanations

    Holocaust, World War II

    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
     wiping
    -0.08
     kjer
    -0.08
     Donc
    -0.07
     Khr
    -0.07
    пен
    -0.07
    ्व
    -0.07
     connaît
    -0.07
    аний
    -0.07
     connaissent
    -0.07
    itten
    -0.07
    POSITIVE LOGITS
     במסגרת
    0.08
     nasc
    0.08
    528
    0.08
     aanbevolen
    0.08
     aposta
    0.08
    lodash
    0.07
    _FRAME
    0.07
     relata
    0.07
     estrutura
    0.07
     lamang
    0.07
    Activations Density 0.004%

    No Known Activations