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. 30761
    Prev
    Next
    INDEX
    Explanations

    Love

    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
     directly
    -0.08
     we'll
    -0.08
    	ax
    -0.08
     substantially
    -0.08
    ิง
    -0.07
    '];↵↵
    -0.07
     materially
    -0.07
    .');↵↵
    -0.07
    ULT
    -0.07
     прямо
    -0.07
    POSITIVE LOGITS
     Pork
    0.08
    Seven
    0.08
     Automobile
    0.08
     Skyrim
    0.08
     ghar
    0.08
     پوست
    0.08
    Seen
    0.08
     Postal
    0.07
     estádio
    0.07
     Pourquoi
    0.07
    Activations Density 0.001%

    No Known Activations