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. 45018
    Prev
    Next
    INDEX
    Explanations

    mental imagery

    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
     inappropriate
    -0.09
     incentiv
    -0.08
     Se
    -0.07
     voting
    -0.07
     andre
    -0.07
    ปล
    -0.07
    excluded
    -0.07
    ice
    -0.07
     primers
    -0.07
     vene
    -0.07
    POSITIVE LOGITS
     spontaneously
    0.10
     возник
    0.09
     beelden
    0.09
     muncul
    0.09
     spontan
    0.09
     imagery
    0.08
     intensidade
    0.08
     vivid
    0.08
     Erfahr
    0.08
     появилась
    0.08
    Activations Density 0.017%

    No Known Activations