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. 42080
    Prev
    Next
    INDEX
    Explanations

    hesitate

    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
     kompat
    -0.09
     Karena
    -0.09
    	ac
    -0.08
     supaya
    -0.08
     Klima
    -0.08
     Drug
    -0.08
     tmp
    -0.07
     πάνω
    -0.07
     Pompe
    -0.07
    Tours
    -0.07
    POSITIVE LOGITS
     willing
    0.09
     ruthless
    0.09
     willingness
    0.09
    狠
    0.08
     willingly
    0.08
     legitimately
    0.08
     reckless
    0.07
     legitimate
    0.07
     legit
    0.07
     적극
    0.07
    Activations Density 0.044%

    No Known Activations