© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24646
    Prev
    Next
    INDEX
    Explanations

    }

    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
    _intr
    -0.07
     emphas
    -0.07
     probable
    -0.07
    常委
    -0.07
    anno
    -0.07
    论坛
    -0.07
    Regardless
    -0.07
    ైనా
    -0.07
    ledger
    -0.07
    ljiv
    -0.07
    POSITIVE LOGITS
    	p
    0.08
     fie
    0.08
    940
    0.08
     Att
    0.08
     
    0.08
     Edith
    0.07
     bullying
    0.07
     doomed
    0.07
    bes
    0.07
     다
    0.07
    Activations Density 0.004%

    No Known Activations