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. 53235
    Prev
    Next
    INDEX
    Explanations

    propose/offer suggestions

    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
     noticing
    -0.08
     meter
    -0.08
     stopwatch
    -0.08
     culto
    -0.08
     individuality
    -0.08
     parses
    -0.08
     আনন্দ
    -0.08
     DOS
    -0.08
     lure
    -0.08
    DOS
    -0.08
    POSITIVE LOGITS
     actionable
    0.16
    措施
    0.16
     उपाय
    0.15
     interventions
    0.15
    Recommendations
    0.14
     proposals
    0.14
     Recommendations
    0.13
     recommendations
    0.13
     प्रस्ताव
    0.13
     추진
    0.13
    Activations Density 0.076%

    No Known Activations