Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111713
    Prev
    Next
    INDEX
    Explanations

    political and military topics

    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
     irritated
    -0.08
     Grammarly
    -0.08
     VBA
    -0.08
     తెలుస
    -0.08
     Buddy
    -0.08
     MLA
    -0.08
     Freel
    -0.08
     Chromebook
    -0.08
     Fol
    -0.08
     trail
    -0.08
    POSITIVE LOGITS
     violent
    0.11
     dangerous
    0.11
    danger
    0.10
     retali
    0.10
     devastating
    0.10
     devast
    0.09
    destroy
    0.09
     controll
    0.09
     आतंक
    0.09
     steril
    0.09
    Activations Density 0.020%

    No Known Activations