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. 106342
    Prev
    Next
    INDEX
    Explanations

    Taking, removing, being with

    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
     (\
    -0.08
     hitting
    -0.08
    501
    -0.08
    708
    -0.08
    300
    -0.07
    ired
    -0.07
     elapsed
    -0.07
    (hit
    -0.07
     hit
    -0.07
    POSITIVE LOGITS
     домой
    0.10
     extraction
    0.09
     extracted
    0.09
     gezogen
    0.09
     extracts
    0.09
     extractor
    0.09
     extracción
    0.09
     custody
    0.09
     Extraction
    0.09
     undan
    0.08
    Activations Density 0.085%

    No Known Activations