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. 42890
    Prev
    Next
    INDEX
    Explanations

    psych

    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
    imer
    -0.09
    =min
    -0.08
    .transpose
    -0.08
     исправ
    -0.07
     Ina
    -0.07
     حفاظ
    -0.07
    =max
    -0.07
     lone
    -0.07
    _WARNING
    -0.07
    очным
    -0.07
    POSITIVE LOGITS
     lifestyle
    0.11
     lifestyles
    0.10
     Lifestyle
    0.10
     criteria
    0.10
     โดย
    0.09
     millennials
    0.08
    Lifestyle
    0.08
     personnalité
    0.08
     personality
    0.08
     บริษัท
    0.08
    Activations Density 0.002%

    No Known Activations