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. 45201
    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
    -0.07
    มั
    -0.07
    ــ
    -0.06
     Huk
    -0.06
    comb
    -0.06
    (dictionary
    -0.06
     conducive
    -0.06
    op
    -0.06
     riscos
    -0.06
     Pron
    -0.06
    POSITIVE LOGITS
     rejoice
    0.09
    数量
    0.09
    	names
    0.09
    _COUNT
    0.08
    424
    0.08
    次数
    0.08
     coordonnées
    0.08
     skinny
    0.08
    ména
    0.08
     Edwin
    0.08
    Activations Density 0.020%

    No Known Activations