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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78802
    Prev
    Next
    INDEX
    Explanations

    US presidents

    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
    .linear
    -0.08
    Trash
    -0.08
     collar
    -0.07
    杂
    -0.07
     collagen
    -0.07
    诀窍
    -0.07
     Rendez
    -0.07
     alph
    -0.07
     uppercase
    -0.07
    丈
    -0.07
    POSITIVE LOGITS
    critic
    0.09
     criticized
    0.09
    -era
    0.09
     राष्ट्रपति
    0.09
     대통령
    0.09
     resign
    0.09
     tenure
    0.08
     incumb
    0.08
     successors
    0.08
     presidency
    0.08
    Activations Density 0.065%

    No Known Activations