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. 52988
    Prev
    Next
    INDEX
    Explanations

    grazing

    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
     cc
    -0.08
    	cc
    -0.08
     ICA
    -0.08
     اچي
    -0.08
    ILLISECONDS
    -0.07
     ISC
    -0.07
    	CC
    -0.07
    াত্র
    -0.07
     ہوتے
    -0.07
    bash
    -0.07
    POSITIVE LOGITS
    وی
    0.08
    不到
    0.08
     omn
    0.08
     intensified
    0.08
    削
    0.08
    艇
    0.07
     biomass
    0.07
     menstru
    0.07
     depletion
    0.07
     Maur
    0.07
    Activations Density 0.010%

    No Known Activations