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. 58208
    Prev
    Next
    INDEX
    Explanations

    or

    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
     disfrut
    -0.09
     Fran
    -0.08
     Dortmund
    -0.08
     അവതരിപ്പ
    -0.08
    	icon
    -0.08
     IW
    -0.08
    泉
    -0.08
    (iterator
    -0.08
     Rhein
    -0.08
    (seed
    -0.07
    POSITIVE LOGITS
     violence
    0.11
     violent
    0.11
     wrongdoing
    0.09
     গুরু
    0.08
     violência
    0.08
     вмеш
    0.08
     dégâts
    0.07
    violent
    0.07
     jailbreak
    0.07
     Violence
    0.07
    Activations Density 0.004%

    No Known Activations