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. 48733
    Prev
    Next
    INDEX
    Explanations

    geometry lines

    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
     synthesis
    -0.08
     producteurs
    -0.08
    -production
    -0.08
     production
    -0.08
     کي
    -0.08
     sukker
    -0.08
     émotion
    -0.07
     нин
    -0.07
    ั
    -0.07
     Evr
    -0.07
    POSITIVE LOGITS
    驰
    0.08
     condiv
    0.08
     asphalt
    0.08
    Shared
    0.08
     gemeinsamen
    0.08
    ︎
    0.08
    ели
    0.08
    _shared
    0.07
    Sharing
    0.07
     pavement
    0.07
    Activations Density 0.014%

    No Known Activations