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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26162
    Prev
    Next
    INDEX
    Explanations

    historical fiction prompts

    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
     Qgs
    -0.08
     ayer
    -0.08
     blender
    -0.08
    lation
    -0.08
     flattened
    -0.08
     destruct
    -0.07
    .conc
    -0.07
    measurement
    -0.07
     Elementor
    -0.07
    than
    -0.07
    POSITIVE LOGITS
     bustling
    0.12
     aboard
    0.10
     pamph
    0.09
     당시
    0.09
     damal
    0.09
     milieu
    0.08
     era
    0.08
     tumult
    0.08
     settlers
    0.08
     époque
    0.08
    Activations Density 0.052%

    No Known Activations