© 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. 175
    Prev
    Next
    INDEX
    Explanations

    builder

    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
    geno
    -0.08
    гор
    -0.08
     gott
    -0.08
    pine
    -0.08
    PASS
    -0.08
    արգ
    -0.07
    	gl
    -0.07
    addle
    -0.07
    	pass
    -0.07
    ุม
    -0.07
    POSITIVE LOGITS
     tarvit
    0.09
    求
    0.08
     خطاب
    0.08
     wist
    0.07
     را
    0.07
     financiamento
    0.07
     itm
    0.07
     indruk
    0.07
     álbum
    0.07
     الاسم
    0.07
    Activations Density 0.000%

    No Known Activations