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. 49888
    Prev
    Next
    INDEX
    Explanations

    makeup and prosthetics

    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
    shortcut
    -0.08
     transparency
    -0.08
     Inbox
    -0.08
     akw
    -0.08
     acknowledging
    -0.08
     acknowled
    -0.08
    Acknowled
    -0.07
    Inbox
    -0.07
    pwd
    -0.07
     wrapper
    -0.07
    POSITIVE LOGITS
     grotes
    0.18
     horrifying
    0.13
     assust
    0.13
     frightening
    0.13
     monstrous
    0.13
     terrifying
    0.11
     creature
    0.11
     страш
    0.11
    怪
    0.11
     bizarre
    0.11
    Activations Density 0.066%

    No Known Activations