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. 77461
    Prev
    Next
    INDEX
    Explanations

    shapeshifting/objects

    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
     Crawford
    -0.09
    ียร์
    -0.08
     challenging
    -0.07
     Beschwerden
    -0.07
     IF
    -0.07
     больших
    -0.07
    ેર
    -0.07
    (authentication
    -0.07
    [...]↵↵
    -0.07
    別
    -0.06
    POSITIVE LOGITS
    -being
    0.09
    -bodied
    0.09
    being
    0.09
     sheen
    0.08
     Yol
    0.08
     parasite
    0.08
    	par
    0.08
    -members
    0.08
    	inst
    0.08
     سم
    0.08
    Activations Density 0.134%

    No Known Activations