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. 120242
    Prev
    Next
    INDEX
    Explanations

    potassium permanganate

    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
    .module
    -0.08
    -from
    -0.08
    frames
    -0.07
     Solar
    -0.07
    _frames
    -0.07
     Frames
    -0.07
    erground
    -0.07
    Ro
    -0.07
    :block
    -0.07
    cei
    -0.07
    POSITIVE LOGITS
     गै
    0.08
     ยู
    0.08
    545
    0.08
    ुरा
    0.08
     ناج
    0.08
    	register
    0.08
     ανο
    0.08
     гири
    0.08
     слиз
    0.08
    єн
    0.08
    Activations Density 0.000%

    No Known Activations