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. 88208
    Prev
    Next
    INDEX
    Explanations

    progressive regressive

    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
     prematurely
    -0.08
     mania
    -0.07
     tlak
    -0.07
    	put
    -0.07
    ystall
    -0.07
    _put
    -0.07
     स्थाप
    -0.07
    _E
    -0.07
    Ez
    -0.07
    Sea
    -0.07
    POSITIVE LOGITS
     umgesetzt
    0.10
     taxing
    0.09
    르게
    0.09
     graduated
    0.09
     torso
    0.08
     الأقل
    0.08
     preferential
    0.08
     proportional
    0.08
     taxes
    0.08
     الأعلى
    0.08
    Activations Density 0.011%

    No Known Activations