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. 29856
    Prev
    Next
    INDEX
    Explanations

    puzzles

    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
     sosial
    -0.09
     sozial
    -0.09
     Bel
    -0.08
    OTTOM
    -0.08
     sosyal
    -0.08
    Bel
    -0.08
    restr
    -0.07
     ndry
    -0.07
    评价
    -0.07
    	camera
    -0.07
    POSITIVE LOGITS
     stratég
    0.08
     leveraging
    0.08
    .pkl
    0.07
     conduit
    0.07
    ifye
    0.07
    .con
    0.07
     phenomenal
    0.07
    573
    0.07
    .decode
    0.07
    atég
    0.07
    Activations Density 0.003%

    No Known Activations