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. 65099
    Prev
    Next
    INDEX
    Explanations

    what

    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
    иг
    -0.07
     excluir
    -0.07
     mecanismos
    -0.07
    orne
    -0.07
    ฤ
    -0.07
     consumir
    -0.07
     něj
    -0.07
    ોખ
    -0.07
     exponential
    -0.07
    िस्त
    -0.07
    POSITIVE LOGITS
    הת
    0.08
     Charity
    0.08
     တ
    0.08
    gings
    0.08
    τευ
    0.08
     चुन
    0.08
    STONE
    0.08
     Hint
    0.08
     ஊ
    0.07
    чес
    0.07
    Activations Density 0.012%

    No Known Activations