Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58943
    Prev
    Next
    INDEX
    Explanations

    image descriptions

    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
     brain
    -0.08
    .endswith
    -0.08
    erson
    -0.08
     webpack
    -0.08
    ason
    -0.07
     Syd
    -0.07
    Sol
    -0.07
    Brain
    -0.07
     heal
    -0.07
     brains
    -0.07
    POSITIVE LOGITS
    ground
    0.09
     Ground
    0.08
     जमीन
    0.08
    foreground
    0.08
     chão
    0.08
    tutorial
    0.08
     trails
    0.08
     grounding
    0.08
     nearer
    0.08
     ground
    0.08
    Activations Density 0.005%

    No Known Activations