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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77370
    Prev
    Next
    INDEX
    Explanations

    Computers in Human Behavior

    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
    Symptoms
    -0.10
    性生活
    -0.09
    免费的
    -0.08
     symptom
    -0.08
    Jazz
    -0.08
    Accordion
    -0.08
    _AUDIO
    -0.08
     muzie
    -0.08
     Symptoms
    -0.08
    Message
    -0.08
    POSITIVE LOGITS
    .predict
    0.09
     selfies
    0.09
     predict
    0.08
     photograph
    0.08
     confidently
    0.08
     referendum
    0.07
     campos
    0.07
     photographs
    0.07
     ponder
    0.07
     kullan
    0.07
    Activations Density 0.001%

    No Known Activations