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. 53090
    Prev
    Next
    INDEX
    Explanations

    state

    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
    	dao
    -0.09
     действий
    -0.08
     consiste
    -0.08
    	callback
    -0.07
     даты
    -0.07
     motivo
    -0.07
     besteh
    -0.07
    udier
    -0.07
     исключ
    -0.07
    	debug
    -0.07
    POSITIVE LOGITS
     connectivity
    0.09
     Connectivity
    0.08
     tonic
    0.08
    Connectivity
    0.08
     tapped
    0.07
     Montenegro
    0.07
    ால
    0.07
    0.07
     junction
    0.07
    Tape
    0.07
    Activations Density 0.001%

    No Known Activations