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. 77947
    Prev
    Next
    INDEX
    Explanations

    rewrite

    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
     Cupertino
    -0.09
     NOAA
    -0.09
     surveyed
    -0.09
    survey
    -0.09
     survey
    -0.08
     Conduct
    -0.08
    _scaled
    -0.08
    	offset
    -0.08
     ystod
    -0.08
    972
    -0.08
    POSITIVE LOGITS
     rewriting
    0.12
    (grammar
    0.11
     removing
    0.11
    Rewrite
    0.10
     rewrite
    0.10
     substitutions
    0.10
    规则
    0.10
     remov
    0.09
    Removing
    0.09
     catalyst
    0.09
    Activations Density 0.009%

    No Known Activations