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. 112864
    Prev
    Next
    INDEX
    Explanations

    expressing liking

    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
    }\\
    -0.08
    verde
    -0.08
     Definition
    -0.07
    ực
    -0.07
    úmero
    -0.07
    显
    -0.07
    zend
    -0.07
    ICAL
    -0.07
     triun
    -0.07
    结束
    -0.07
    POSITIVE LOGITS
     nostalgic
    0.09
     favorites
    0.09
     nostalg
    0.09
     apprécié
    0.08
    .Preference
    0.08
    Taste
    0.08
     dissatisfaction
    0.08
     notified
    0.08
     casser
    0.08
    quires
    0.08
    Activations Density 0.024%

    No Known Activations