© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45225
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    준
    -0.08
    .ma
    -0.08
     Caldwell
    -0.08
    hle
    -0.07
    ’S
    -0.07
    .Math
    -0.07
    assen
    -0.07
     பிரத
    -0.07
     ®
    -0.07
    igsaw
    -0.07
    POSITIVE LOGITS
    Bat
    0.09
     rekla
    0.08
     introduced
    0.08
    	var
    0.07
    трым
    0.07
     var
    0.07
     "{\"
    0.07
     pasted
    0.07
    設定
    0.07
    bat
    0.07
    Activations Density 0.001%

    No Known Activations