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. 12380
    Prev
    Next
    INDEX
    Explanations

    computer hardware specifications

    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
    Meth
    -0.08
    -dialog
    -0.08
     Meth
    -0.08
    -modal
    -0.07
    Modal
    -0.07
    	Mat
    -0.07
    Paginator
    -0.07
    律师
    -0.07
    	bt
    -0.07
     lawyers
    -0.07
    POSITIVE LOGITS
    avicon
    0.08
     MHz
    0.08
     laste
    0.08
     eisen
    0.08
     sluggish
    0.08
     SSE
    0.07
     noget
    0.07
     vitesse
    0.07
     spænd
    0.07
    _By
    0.07
    Activations Density 0.006%

    No Known Activations