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. 43001
    Prev
    Next
    INDEX
    Explanations

    fff

    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
    ifficult
    -0.09
    uros
    -0.09
     Vertrags
    -0.08
    isaties
    -0.08
    arries
    -0.08
     unus
    -0.08
     Boilers
    -0.08
     Habana
    -0.07
     Tonight
    -0.07
     Ка
    -0.07
    POSITIVE LOGITS
    -white
    0.09
     enclosure
    0.09
     white
    0.09
    白
    0.09
     White
    0.09
    White
    0.08
    干
    0.08
    fff
    0.08
     surroundings
    0.08
    white
    0.08
    Activations Density 0.003%

    No Known Activations