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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1626
    Prev
    Next
    INDEX
    Explanations

    eyeliner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    533
    -0.08
     foret
    -0.08
     zast
    -0.07
    liegt
    -0.07
     pave
    -0.07
    047
    -0.07
     atten
    -0.07
     перек
    -0.07
     elf
    -0.07
     ism
    -0.07
    POSITIVE LOGITS
    osis
    0.09
     Mary
    0.08
    shirt
    0.08
     Spots
    0.08
    Club
    0.08
     eyeliner
    0.08
     Hyderabad
    0.08
    斗
    0.08
    ətbi
    0.07
    paper
    0.07
    Activations Density 0.003%

    No Known Activations